Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 77521
    Prev
    Next
    INDEX
    Explanations

    specific programming-related terms and concepts related to game development and logic implementation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    tic-tac-toe board game

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hirsch
    -0.36
    Heraus
    -0.36
    不服
    -0.34
     Kinney
    -0.34
    }{*}{
    -0.33
    mad
    -0.33
     brisa
    -0.33
     
    -0.33
     Congress
    -0.33
    avenir
    -0.32
    POSITIVE LOGITS
    EndGlobalSection
    0.55
    OGND
    0.54
    новништво
    0.54
    AndEndTag
    0.54
     Wikimedijinoj
    0.53
    CloseOperation
    0.52
     iprot
    0.49
    SequentialGroup
    0.48
    BeginContext
    0.47
    IANGLES
    0.47
    Activations Density 0.053%

    No Known Activations