© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16242
    Prev
    Next
    INDEX
    Explanations

    references to player performances and statistics in sports contexts

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

    American football (NFL/quarterback/preseason)

    np_acts-logits-general · gemini-2.0-flash

    sports careers quarterback

    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
     läßt
    -0.69
    🏻‍♀️
    -0.60
     Judith
    -0.56
    arker
    -0.56
     orientation
    -0.55
     Whilst
    -0.55
    cyjna
    -0.55
    Chai
    -0.55
     Bapak
    -0.55
    webElement
    -0.54
    POSITIVE LOGITS
     offseason
    0.83
     coaches
    0.78
     postseason
    0.77
     playoff
    0.71
     coach
    0.71
     offensively
    0.70
     teammates
    0.70
     preseason
    0.67
     ESPN
    0.66
     coaching
    0.66
    Activations Density 1.064%

    No Known Activations