© 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. 11084
    Prev
    Next
    INDEX
    Explanations

    references to abuse, violence, and oppressive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     candidate
    -0.45
     Admit
    -0.40
     partire
    -0.40
    ínű
    -0.39
    ۪
    -0.39
     otomatig
    -0.39
     ну
    -0.39
     settled
    -0.39
     merito
    -0.39
     advisable
    -0.38
    POSITIVE LOGITS
     violence
    0.76
     Violence
    0.73
     Gewalt
    0.72
     kekerasan
    0.71
    Violence
    0.70
    violence
    0.66
     abuse
    0.63
     abuso
    0.62
     abusive
    0.61
     violencia
    0.60
    Activations Density 0.288%

    No Known Activations