© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4097
    Prev
    Next
    INDEX
    Explanations

    references to games and gaming-related terminology

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

    references to video games or game development.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     Clough
    -0.52
    ="#"><
    -0.51
     menahan
    -0.49
     úteis
    -0.48
     necesitar
    -0.44
     trusted
    -0.43
    atriz
    -0.43
     Wh
    -0.43
     Utilizamos
    -0.42
     útiles
    -0.42
    POSITIVE LOGITS
     Game
    1.17
    Game
    1.16
     game
    1.13
    game
    1.05
     GAME
    1.05
    getGame
    1.01
    GAME
    0.95
     games
    0.95
     Games
    0.90
     GAMES
    0.90
    Activations Density 0.029%

    No Known Activations