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. 8163
    Prev
    Next
    INDEX
    Explanations

    references to books, articles, and other forms of media

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

    Nouns representing media formats, publications, or creative works that are being referenced or discussed.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     typically
    -0.34
    Floor
    -0.31
    floor
    -0.31
     litri
    -0.31
     democrática
    -0.30
     vloer
    -0.30
     mergeFrom
    -0.29
    Ỏ
    -0.29
     unre
    -0.29
     fondament
    -0.28
    POSITIVE LOGITS
    RenderAtEndOf
    0.77
     resourceCulture
    0.73
    TypedDataSet
    0.71
     betweenstory
    0.68
    aarrggbb
    0.68
    AnchorTagHelper
    0.68
    şört
    0.66
    FormTagHelper
    0.65
    ngrx
    0.64
    -------
    0.63
    Activations Density 0.159%

    No Known Activations