© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3239
    Prev
    Next
    INDEX
    Explanations

    references to sports events and notable sporting achievements

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

    references to rugby union players, teams, and sporting achievements.

    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
     energy
    -0.40
     charité
    -0.39
     INTE
    -0.38
    PreExecute
    -0.38
     chemical
    -0.38
     oil
    -0.38
    オイル
    -0.37
    tigs
    -0.37
     girasol
    -0.36
     Vikipedi
    -0.35
    POSITIVE LOGITS
     rugby
    1.01
     Rugby
    0.98
     scrum
    0.96
    Rugby
    0.93
    rugby
    0.93
    🏉
    0.77
     Scrum
    0.71
     flan
    0.67
     CreateTagHelper
    0.62
     Heineken
    0.61
    Activations Density 0.086%

    No Known Activations