© 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. 2895
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential hazards or risks associated with various activities and objects

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    hazardous or dangerous situations and their potential consequences.

    oai_token-act-pair · claude-4-5-haiku
    Triggered 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
    Negative Logits
     hẳn
    -0.38
     complimented
    -0.37
     sih
    -0.36
    Bibliografia
    -0.35
    yonel
    -0.33
    /**
    -0.33
     überzeugen
    -0.33
     erfü
    -0.32
     помогают
    -0.32
    ন্
    -0.32
    POSITIVE LOGITS
     potentially
    1.70
     potential
    1.63
     danger
    1.60
     dangers
    1.60
     risks
    1.57
    potentially
    1.55
     risk
    1.53
    Potential
    1.52
     potencial
    1.49
    potential
    1.49
    Activations Density 1.152%

    No Known Activations