© 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. 1300
    Prev
    Next
    INDEX
    Explanations

    references to governmental and educational institutions

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

    governmental and institutional references including ministries, courts, and official bodies.

    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
    Winnipeg
    -0.59
    Montreal
    -0.59
     Winnipeg
    -0.58
     Tbilisi
    -0.52
     Montreal
    -0.50
     петербург
    -0.50
     Afrikaans
    -0.48
     Balkans
    -0.47
    Alaska
    -0.47
     Азии
    -0.47
    POSITIVE LOGITS
     Republic
    0.97
     republic
    0.78
    Republic
    0.74
     Kingdom
    0.64
     Republik
    0.63
     REPUBLIC
    0.62
     Federation
    0.62
     Federal
    0.57
    republic
    0.55
     Union
    0.53
    Activations Density 0.446%

    No Known Activations