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 - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 108
    Prev
    Next
    INDEX
    Explanations

    play-by-play actions and scoring events in sports narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.73
    IVEREF
    -0.63
     Theſe
    -0.57
    AndEndTag
    -0.56
     endforeach
    -0.54
     pouvoit
    -0.54
    Cyfarwyddwr
    -0.53
    RenderAtEndOf
    -0.53
     StatelessWidget
    -0.53
    ſelf
    -0.52
    POSITIVE LOGITS
     inning
    0.40
     score
    0.40
     Score
    0.36
    scored
    0.36
    score
    0.35
     scoring
    0.35
     Garn
    0.34
    setCharacter
    0.34
     scoreboard
    0.34
    IContainer
    0.34
    Activations Density 0.134%

    No Known Activations