© 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. 2183
    Prev
    Next
    INDEX
    Explanations

    references to safety and security in various contexts

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

    the word "safety" and related risk/protective concepts.

    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
     виправивши
    -0.44
     başına
    -0.38
     fofo
    -0.35
     Räume
    -0.34
     Chwiliwch
    -0.33
    <>
    -0.33
     Demokratie
    -0.32
    verkehr
    -0.32
     Substanz
    -0.31
     gig
    -0.30
    POSITIVE LOGITS
     considerations
    0.83
     improvements
    0.78
     concerns
    0.77
    лтемелер
    0.73
     improvement
    0.72
    concerns
    0.71
     issues
    0.71
     Concerns
    0.68
     Improvements
    0.66
    Improvements
    0.65
    Activations Density 0.684%

    No Known Activations