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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 77360
    Prev
    Next
    INDEX
    Explanations

    programming terms and keywords related to UI and database operations

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

    mandate issue, Pack, Content, briefs, opts

    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
    sidemargin
    -0.80
    ContentLoaded
    -0.76
     hoạch
    -0.67
    RectangleBorder
    -0.62
    flashdata
    -0.61
     Smal
    -0.59
    AnimationsModule
    -0.57
    ãng
    -0.57
     kiệm
    -0.57
    HostException
    -0.57
    POSITIVE LOGITS
    yarnpkg
    1.08
     kaarangay
    0.99
     autorytatywna
    0.94
     ویکی‌پدی
    0.86
     Италијани
    0.82
     nahilalakip
    0.76
    hoeddwyd
    0.73
     pinulongan
    0.71
    RTGC
    0.70
     يتيمه
    0.69
    Activations Density 0.446%

    No Known Activations