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. 29251
    Prev
    Next
    INDEX
    Explanations

    dialogue and quotations in text

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

    quotes including "he said"

    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
     HasFactory
    -0.59
     defaultstate
    -0.58
     >=",
    -0.57
    AddTagHelper
    -0.55
    MigrationBuilder
    -0.50
    aktur
    -0.50
     opérés
    -0.50
     ब्रेकडाउन
    -0.50
    TypedDataSet
    -0.49
     incluyendo
    -0.48
    POSITIVE LOGITS
    principalColumn
    0.47
     Bison
    0.38
     Lime
    0.35
    terase
    0.35
     Salesforce
    0.34
     Blazer
    0.34
     Dayton
    0.34
    urtstag
    0.34
    IActionResult
    0.33
    ail
    0.33
    Activations Density 0.012%

    No Known Activations