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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 15185
    Prev
    Next
    INDEX
    Explanations

    instances of player performance and dynamics within a team context

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

    sports commentary discussing team performance, player decisions, and managerial tactics.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +:+
    -0.54
     препратки
    -0.50
    
    -0.46
    principalTable
    -0.46
    interopRequire
    -0.44
    andoah
    -0.44
    Cuba
    -0.43
     Oaxaca
    -0.41
     Kauai
    -0.41
    harley
    -0.41
    POSITIVE LOGITS
     footballers
    0.87
     striker
    0.86
     midfield
    0.85
     goalkeeper
    0.84
     midfielder
    0.83
     football
    0.81
     UEFA
    0.81
     FIFA
    0.80
     Football
    0.78
     players
    0.76
    Activations Density 0.472%

    No Known Activations