© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 671
    Prev
    Next
    INDEX
    Explanations

    specific game mechanics and interactions related to player engagement

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

    video games, quests, or game experiences

    np_acts-logits-general · gemini-2.0-flash

    game worlds and player quests

    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
    protoimpl
    -0.44
     WEDDING
    -0.42
     Exactos
    -0.39
     autorytatywna
    -0.39
    migrationBuilder
    -0.39
    참고
    -0.38
     contactez
    -0.37
     læng
    -0.37
     OUTPUT
    -0.37
     TRAN
    -0.37
    POSITIVE LOGITS
     walkthrough
    0.47
    ksamkeit
    0.45
    gebung
    0.42
    oa̍t
    0.40
    rinth
    0.40
     تعدى
    0.40
    mpä
    0.40
     chronologically
    0.40
     linearly
    0.39
     հղումներ
    0.38
    Activations Density 0.118%

    No Known Activations