Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 8105
    Prev
    Next
    INDEX
    Explanations

    statistical performance metrics related to sports, specifically football

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

    Numbers followed by "yards"

    np_acts-logits-general · gemini-2.0-flash

    football yardage statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.66
    windowFixed
    -0.64
     MyBatis
    -0.56
     שוליים
    -0.54
    eBook
    -0.54
    onAttach
    -0.54
    bars
    -0.53
     Commencez
    -0.53
     Jubilee
    -0.52
     onPage
    -0.52
    POSITIVE LOGITS
     yards
    0.88
     yard
    0.85
    yards
    0.74
     net
    0.72
    yard
    0.71
     rushing
    0.65
    net
    0.65
    YARD
    0.60
     rush
    0.60
    Net
    0.60
    Activations Density 0.132%

    No Known Activations