© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 14536
    Prev
    Next
    INDEX
    Explanations

    terms related to sports and athletic performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.63
     betweenstory
    -0.52
    RegressionTest
    -0.48
     '\\;'
    -0.46
     surla
    -0.46
    irited
    -0.45
    corner
    -0.44
    endphp
    -0.44
    addGap
    -0.44
     Италијани
    -0.43
    POSITIVE LOGITS
     tackle
    0.66
     blocking
    0.65
     tackles
    0.58
     guard
    0.58
     interior
    0.57
     blocker
    0.57
     snapping
    0.55
     Blocking
    0.54
     snapped
    0.53
     Tackle
    0.53
    Activations Density 0.204%

    No Known Activations