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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 4963
    Prev
    Next
    INDEX
    Explanations

    references to card games and their mechanics

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

    Board or video games

    np_acts-logits-general · gemini-2.0-flash

    games and game components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeConstraints
    -0.84
    ьаж
    -0.73
     sólidos
    -0.49
    tvguidetime
    -0.49
    ToBounds
    -0.48
    rense
    -0.48
    saraba
    -0.47
    Haber
    -0.46
     planta
    -0.45
    featureID
    -0.44
    POSITIVE LOGITS
     game
    0.74
     games
    0.72
     Spiele
    0.70
     deck
    0.70
    出版年
    0.69
     Hasbro
    0.66
     decks
    0.65
     Game
    0.65
     jeu
    0.64
    Game
    0.62
    Activations Density 0.319%

    No Known Activations