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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 105152
    Prev
    Next
    INDEX
    Explanations

    conjunctions and other linking words that establish relationships between clauses or ideas

    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
    VersionUID
    -0.44
    .
    -0.35
    enumi
    -0.34
    ineno
    -0.34
    MathML
    -0.32
    zarchiwizowane
    -0.30
    flashdata
    -0.30
    rašymas
    -0.30
    点了点头
    -0.29
    AddHtmlAttribute
    -0.28
    POSITIVE LOGITS
     Infórmanos
    0.74
     autorytatywna
    0.68
     CreateTagHelper
    0.62
    цездатний
    0.58
    يكب
    0.56
     виправивши
    0.55
     PIP
    0.52
    hoeddwyd
    0.52
    뀜
    0.52
     Numerade
    0.50
    Activations Density 0.260%

    No Known Activations