Language Model Interpretability Team, Google DeepMind
    Exploring
    Gemma Scope
    An Introduction to AI Interpretability and the Inner Workings of Gemma 2 2B
    👋 Hello!
    The inner workings of modern AIs are a mystery. This is because AIs are language models that are grown, not designed.
    The science of understanding what happens inside AI is called interpretability.
    This demo is a beginner-friendly introduction to interpretability that explores an AI model called Gemma 2 2B. It also contains interesting and relevant content even for those already familiar with the topic.
    🔧 Get Started
    🧑‍🔬
    Browse SAEs
    Already know what SAEs are?