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. 77042
    Prev
    Next
    INDEX
    Explanations

    references to the "document" object in JavaScript

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Pfar
    -0.51
    s
    -0.48
     său
    -0.47
     pitié
    -0.43
     Bundesrepublik
    -0.42
     Weinberg
    -0.42
     aérea
    -0.42
     ältere
    -0.42
     Autres
    -0.41
     ataupun
    -0.41
    POSITIVE LOGITS
     document
    1.02
     Document
    0.95
    ocument
    0.93
    document
    0.92
    Document
    0.89
     DOCUMENT
    0.82
     documents
    0.81
     Documents
    0.78
    getDocument
    0.75
    DOCUMENT
    0.73
    Activations Density 0.001%

    No Known Activations