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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7638
    Prev
    Next
    INDEX
    Explanations

    references to games and gaming terminology

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

    "game" followed by certain words

    np_acts-logits-general · gemini-2.0-flash

    game call, game called, game department, game is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bambú
    -0.39
     Glieder
    -0.39
     pères
    -0.38
     Zeugen
    -0.38
     esquí
    -0.37
     prêtres
    -0.37
     propietarios
    -0.36
     sabiduría
    -0.35
    según
    -0.35
     Auss
    -0.35
    POSITIVE LOGITS
     Game
    1.05
    Game
    0.93
     GAME
    0.89
     game
    0.88
    game
    0.86
    ⓧ
    0.83
    GAME
    0.81
     Games
    0.79
    getGame
    0.78
     games
    0.73
    Activations Density 0.088%

    No Known Activations