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. 4357
    Prev
    Next
    INDEX
    Explanations

    references to coaching changes and personnel decisions in sports

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

    football coaches

    np_acts-logits-general · gemini-2.0-flash

    coach and coaching roles

    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
    TypedDataSet
    -0.84
    WireFormatLite
    -0.70
    Erreferentziak
    -0.62
     Jefus
    -0.61
    )_/¯
    -0.59
    repres
    -0.59
    Begriffsklä
    -0.57
    ItemLayout
    -0.57
    */].
    -0.57
    ppuden
    -0.56
    POSITIVE LOGITS
     coaching
    1.51
     coach
    1.34
    Coaching
    1.26
     Coaching
    1.23
     coaches
    1.20
     Coach
    1.15
     coached
    1.14
    coaching
    1.12
    coach
    1.12
     COACH
    1.06
    Activations Density 0.161%

    No Known Activations