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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9398
    Prev
    Next
    INDEX
    Explanations

    details related to sports events, particularly playoff games and their outcomes

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

    Scores or progress in sports matches

    np_acts-logits-general · gemini-2.0-flash

    game scores and series results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    Parcelize
    -0.67
    sidemargin
    -0.65
     GenerationType
    -0.63
     InputDecoration
    -0.62
    WebVitals
    -0.61
    DotNetBar
    -0.60
     unknownFields
    -0.58
    WireFormatLite
    -0.58
    SharedCtor
    -0.58
    MessageTagHelper
    -0.57
    POSITIVE LOGITS
     series
    0.77
    series
    0.66
     straight
    0.62
     pinulongan
    0.62
     sets
    0.60
    Series
    0.60
     sweep
    0.58
     Series
    0.57
    govina
    0.57
     serie
    0.57
    Activations Density 0.102%

    No Known Activations