Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 5595
    Prev
    Next
    INDEX
    Explanations

    incidents involving violence and arrests

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

    police shooting victims

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    tvguidetime
    -0.51
    ViewImports
    -0.46
     autorytatywna
    -0.46
    AndroidJUnit
    -0.46
    脚注の使い方
    -0.45
     consonants
    -0.45
     maestra
    -0.44
    MigrationBuilder
    -0.44
     newOwner
    -0.43
    UserScript
    -0.42
    POSITIVE LOGITS
    ⎪
    0.43
     "..\..\..\
    0.37
    drawSprites
    0.36
    SupportActionBar
    0.35
    uruhan
    0.35
    optionalTypeArgs
    0.35
     nás
    0.34
    Datuak
    0.33
     kwiat
    0.33
     Jai
    0.33
    Activations Density 0.020%

    No Known Activations