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

    Neuronpedia

    APICircuit 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. 29319
    Prev
    Next
    INDEX
    Explanations

    titles and names of video games

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

    racing games, fantasy games

    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
    LookAnd
    -0.48
     ostavi
    -0.40
    Хьажоргаш
    -0.40
    CurrentValue
    -0.38
    WriteAttribute
    -0.37
     fieldNum
    -0.37
    endphp
    -0.37
    WebServlet
    -0.37
    moveToFirst
    -0.36
    ViewBag
    -0.35
    POSITIVE LOGITS
    IndentedString
    0.55
    ">:
    0.47
    Influence
    0.46
     newBuilder
    0.45
    وفاته
    0.44
    cookieParser
    0.43
     OFDb
    0.43
    ulipas
    0.43
     Influence
    0.43
    kloped
    0.41
    Activations Density 0.164%

    No Known Activations