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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9744
    Prev
    Next
    INDEX
    Explanations

    topics related to video games and gameplay mechanics

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

    Following game-related terms

    np_acts-logits-general · gemini-2.0-flash

    car drives, rail shooter, it explodes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    IntoConstraints
    -0.77
    phosa
    -0.71
     ModelExpression
    -0.64
    MENAFN
    -0.60
    CloseOperation
    -0.60
    CppMethod
    -0.59
    makeConstraints
    -0.59
    URLException
    -0.59
    LayoutPanel
    -0.59
     يتيمه
    -0.58
    POSITIVE LOGITS
    flä
    0.36
    maz
    0.33
     caisse
    0.32
     menyus
    0.32
     Geister
    0.32
     squee
    0.32
    ino
    0.31
     Mar
    0.31
     Kral
    0.30
    ائ
    0.30
    Activations Density 0.068%

    No Known Activations