© 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. 20-GEMMASCOPE-RES-16K
    11. 5298
    Prev
    Next
    INDEX
    Explanations

    references to crime rates and safety in society

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

    words related to race and racial issues.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    descriptions of crimes, violent or dangerous incidents, and accidents—often in a statistical or report-like context emphasizing rates, counts, or fatalities.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    statistical descriptions of incidents, accidents, or violence, especially when quantified with numbers or rates.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     înal
    -0.44
    ędziesz
    -0.42
    ksesta
    -0.40
     tatuagem
    -0.38
    ніципалі
    -0.36
    OGND
    -0.36
     essenziale
    -0.36
     صوتيه
    -0.36
     schoenen
    -0.36
     الحره
    -0.36
    POSITIVE LOGITS
     incidents
    0.92
     incident
    0.73
     deaths
    0.72
     Incidents
    0.71
     victims
    0.70
     cases
    0.66
     crimes
    0.66
     fatalities
    0.65
     occurrences
    0.64
     victim
    0.64
    Activations Density 0.256%

    No Known Activations