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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6533
    Prev
    Next
    INDEX
    Explanations

    references to winning or awards in competitive contexts

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

    The words "win" or "winner"

    np_acts-logits-general · gemini-2.0-flash

    won or winner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .*")]
    -0.61
     المعيارى
    -0.60
     DataTypes
    -0.58
    brtc
    -0.56
    addGap
    -0.54
    ंदीखरीदारी
    -0.53
     ostavi
    -0.53
    <?
    -0.52
     GBIF
    -0.52
    VersionUID
    -0.52
    POSITIVE LOGITS
     won
    1.16
     winning
    1.00
    Winning
    0.93
    Won
    0.92
     winner
    0.90
    won
    0.90
    winning
    0.89
     Won
    0.87
     win
    0.85
    Winner
    0.85
    Activations Density 0.106%

    No Known Activations