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. 56555
    Prev
    Next
    INDEX
    Explanations

    mentions of specific programming libraries and concepts related to web automation and multiprocessing

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

    deno, multiprocessing, asyncio context

    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
    eradish
    -0.34
    "][
    -0.31
    ()][
    -0.30
     createState
    -0.30
    mær
    -0.30
    }">
    -0.29
     Lampung
    -0.29
    }<
    -0.29
    ">'
    -0.28
    Online
    -0.28
    POSITIVE LOGITS
     asyncio
    2.17
    asyncio
    1.38
    peteer
    0.95
     aio
    0.87
    ToListAsync
    0.84
    getDoctrine
    0.76
    ########.
    0.73
     tokio
    0.71
    complexContent
    0.69
    IntoConstraints
    0.68
    Activations Density 0.001%

    No Known Activations