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
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 129892
    Prev
    Next
    INDEX
    Explanations

    patterns of code structure and indentation

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

    HTML, XML, code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     neutral
    -0.39
     Ab
    -0.37
    gebnisse
    -0.35
    空
    -0.35
    原
    -0.34
    InSection
    -0.34
    Zwischen
    -0.34
     spot
    -0.33
     Neutral
    -0.33
    ığı
    -0.33
    POSITIVE LOGITS
     ModelExpression
    0.69
     fédé
    0.65
    Datuak
    0.61
     propOrder
    0.59
    complexContent
    0.57
     ब्रेकडाउन
    0.57
     GenerationType
    0.57
    endpush
    0.57
     مشين
    0.56
    ]")]
    0.56
    Activations Density 0.009%

    No Known Activations