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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-131K
    6. 122857
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols or notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    tvguidetime
    -0.49
    makedirs
    -0.49
    )="
    -0.48
     تعدى
    -0.46
    -------------</
    -0.46
     ब्रेकडाउन
    -0.45
    putan
    -0.45
    CSRF
    -0.45
    //----
    -0.45
    IBOutlet
    -0.45
    POSITIVE LOGITS
    amssymb
    4.56
    ssymb
    1.04
    adaptiveStyles
    0.50
    ignoire
    0.47
     resourceCulture
    0.46
    ViewFeatures
    0.46
    amsmath
    0.46
     kasarigan
    0.46
     nakalista
    0.46
     kaynağından
    0.45
    Activations Density 0.000%

    No Known Activations