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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 13323
    Prev
    Next
    INDEX
    Explanations

    references to betting odds and gaming terminology

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

    Betting and gambling contexts

    np_acts-logits-general · gemini-2.0-flash

    betting and predictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ngdoc
    -0.56
    #
    -0.54
    parsedMessage
    -0.50
    Portail
    -0.49
    VersionUID
    -0.48
    cshtml
    -0.48
    MemoryWarning
    -0.47
    rawDesc
    -0.42
    دانشنامهٔ
    -0.42
     ciudadana
    -0.42
    POSITIVE LOGITS
     betting
    0.70
     bets
    0.59
     Bets
    0.57
     Betting
    0.57
    Prediction
    0.55
    Betting
    0.53
     Prediction
    0.52
     bet
    0.52
    Predictions
    0.50
    bets
    0.49
    Activations Density 0.103%

    No Known Activations