© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16185
    Prev
    Next
    INDEX
    Explanations

    code structures and logic related to a game implementation, particularly for Tic-Tac-Toe

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

    Game board representations and logic

    np_acts-logits-general · gemini-2.0-flash

    game board logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.81
    RenderAtEndOf
    -0.78
     ujednoznacz
    -0.76
    WriteAttribute
    -0.66
     >=",
    -0.65
     typelib
    -0.64
    󠁴
    -0.62
    oneofs
    -0.56
    MessageOf
    -0.55
    audiovisuel
    -0.54
    POSITIVE LOGITS
     tiles
    1.05
     tile
    1.00
     grid
    0.96
     Tile
    0.95
     board
    0.95
    grid
    0.89
    Tile
    0.84
     cell
    0.83
    Board
    0.81
     Tiles
    0.81
    Activations Density 0.354%

    No Known Activations