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. 24541
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their actions within a narrative

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

    Proper nouns or pronouns representing key entities who are actors or subjects in formal texts, particularly legal documents, sports coverage, and narratives.

    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
    WithIOException
    -0.56
    \{\\
    -0.55
     مشين
    -0.54
    IUrlHelper
    -0.54
     informée
    -0.53
     Anatom
    -0.53
    anatom
    -0.52
    majánló
    -0.52
    Anatom
    -0.52
     anatom
    -0.50
    POSITIVE LOGITS
     chuckled
    0.34
    ectady
    0.31
     ostavi
    0.31
    She
    0.29
    ::*;
    0.28
     resigned
    0.28
     Falle
    0.28
     Blech
    0.28
    付
    0.27
    setContentView
    0.27
    Activations Density 0.058%

    No Known Activations