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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 6653
    Prev
    Next
    INDEX
    Explanations

    information related to NFL teams and players, especially focusing on performance and player statistics

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

    NFL, football positions, or offensive plays

    np_acts-logits-general · gemini-2.0-flash

    offensive line and football positions

    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
    发表于
    -0.49
     aDecoder
    -0.43
     kasarigan
    -0.39
     tenuto
    -0.39
    brtc
    -0.39
    niaus
    -0.39
    interopRequire
    -0.38
    jeeling
    -0.38
     pol
    -0.38
    BeanUtils
    -0.37
    POSITIVE LOGITS
     NFL
    0.67
     Football
    0.66
    NFL
    0.65
     football
    0.60
    football
    0.58
    🏈
    0.57
    Football
    0.56
     ModelRenderer
    0.53
     FOOTBALL
    0.52
    kheim
    0.48
    Activations Density 0.327%

    No Known Activations