Greater risk-taking behaviors, such as alcohol experimentation, are associated with different patterns of brain functioning in regions implicated in reward (nucleus accumbens, NA) and cognitive control (inferior frontal gyrus, IFG). These neural features have been observed in youth with greater risk-taking tendencies prior to substance use initiation, suggesting NA-IFG disruption may serve as an early marker for subsequent substance use disorders. Prospective studies are needed to determine if NA-IFG disruption predicts future substance use in school-age children, including those with minimal use of alcohol (e.g., sipping). The present large-sample prospective study sought to: (1) examine alcohol sipping at ages 9-10 as a potential behavioral indicator of concurrent underlying altered neural responsivity to reward, and (2) determine if alcohol sipping and NA-IFG activation at ages 9-10 predicts increased alcohol use at ages 10-11. This project used data from the baseline (Time 1) and two-year follow-up (Time 2) assessments of the Adolescent Brain Cognitive Development (ABCD) Study (Release 3.0). Support Vector Machine (SVM) learning determined if: (1) NA-IFG neural activity could correctly identify youth who reported alcohol sipping at Time 1 (n = 7409), and (2) NA-IFG and alcohol sipping frequency at Time 1 could correctly identify youth who reported drinking alcohol at Time 2 (n = 4000). The context in which youth first tried sips of alcohol was also characterized (e.g., with or without parental permission, as part of a religious experience). Approximately 24% of the sample reported having tried sips of alcohol by ages 9-10, with 76% reporting doing so outside of the context of a religious ceremony. The first SVM model classified youth according to alcohol sipping status at Time 1 with an accuracy of .35 (sensitivity = .24, specificity = .80). The second SVM model classified youth according to alcohol drinking status at Time 2 with an accuracy of .76 (sensitivity = .21, specificity = .91). Linear regression demonstrated that frequency of alcohol sipping at Time 1 predicted frequency of alcohol use at Time 2 (p < .001, adjusted r2 =.08). Activity in the three subsections of the IFG at Time 1 predicted activity in those same regions at Time 2 (all ps < .02). All other relationships were not significant. Early sips of alcohol, across environmental contexts, appear to predict frequency of alcohol use in early adolescence. Findings do not provide strong evidence for minimal early alcohol use (i.e., sipping) as a behavioral marker of underlying alterations in NA-IFG neural responsivity to reward. Improving our understanding of the neural and behavioral factors that indicate a greater propensity for future substance use is crucial for identifying at-risk youth and potential targets for preventative efforts.