© 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. 5345
    Prev
    Next
    INDEX
    Explanations

    references to trade unions and their impact on labor relations

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

    the word "trade" followed by related terms indicating exchanges or comparisons of costs and benefits.

    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
     Ewig
    -0.36
    guém
    -0.35
     silicona
    -0.35
     الأمر
    -0.35
     Drit
    -0.34
    icação
    -0.34
     Regierungs
    -0.34
    5
    -0.33
    posições
    -0.33
     Entsch
    -0.33
    POSITIVE LOGITS
    Trade
    0.90
     Trade
    0.90
     trade
    0.83
    trade
    0.83
     TRADE
    0.79
    Trades
    0.69
    TRADE
    0.68
     trades
    0.67
     Trades
    0.66
     traded
    0.66
    Activations Density 0.103%

    No Known Activations