© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2250
    Prev
    Next
    INDEX
    Explanations

    mentions of sports teams and their performance

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

    historical sports records and statistics, particularly win-loss records and season performance data.

    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
     tomorrow
    -0.74
     tonight
    -0.71
     today
    -0.67
     amanhã
    -0.62
     yesterday
    -0.57
     new
    -0.57
     demain
    -0.57
    これから
    -0.56
     domani
    -0.56
     depuis
    -0.55
    POSITIVE LOGITS
     damals
    1.06
     famously
    1.05
     damaligen
    0.98
     damal
    0.96
     pernah
    0.88
     memorable
    0.86
    当年
    0.83
     aquel
    0.82
     infamous
    0.81
    当时的
    0.81
    Activations Density 0.626%

    No Known Activations