© 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. 3044
    Prev
    Next
    INDEX
    Explanations

    references to historical atrocities, specifically the Holocaust

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

    historical atrocities, genocide, and mass killings.

    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
    jaqueta
    -0.48
     zmar
    -0.44
    muñeca
    -0.43
    chaqueta
    -0.40
     pegatinas
    -0.40
     kuin
    -0.39
     figliu
    -0.39
    ėjas
    -0.39
     bail
    -0.39
    ografija
    -0.39
    POSITIVE LOGITS
     genocide
    1.19
     genoc
    1.05
     massacres
    1.03
     extermination
    1.00
     massacre
    1.00
     Genocide
    0.96
     massac
    0.85
     exter
    0.84
     slaughter
    0.82
     atrocities
    0.81
    Activations Density 0.417%

    No Known Activations