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. 3778
    Prev
    Next
    INDEX
    Explanations

    terms related to gambling and financial metrics

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

    probability, betting odds, or losses

    np_acts-logits-general · gemini-2.0-flash

    betting odds and classification scores

    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
    rungsseite
    -0.59
     ویکی‌پدیا
    -0.50
    Życiorys
    -0.49
    msgTypes
    -0.47
     OMITBAD
    -0.46
     Infórmanos
    -0.45
    argout
    -0.45
     famí
    -0.44
    Biblia
    -0.43
     kasarigan
    -0.42
    POSITIVE LOGITS
     odds
    0.49
    Odds
    0.48
     Odds
    0.45
    odds
    0.44
    logits
    0.43
    softmax
    0.43
     Betting
    0.42
     betting
    0.42
    */].
    0.41
     newOwner
    0.39
    Activations Density 0.360%

    No Known Activations