© 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. 37-GEMMASCOPE-RES-16K
    11. 9123
    Prev
    Next
    INDEX
    Explanations

    references to extreme political ideologies and associated figures

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     verzichten
    -0.34
    WithIOException
    -0.34
     kebiasaan
    -0.32
     nerfed
    -0.31
    localctx
    -0.31
     tuturor
    -0.30
    asanjo
    -0.30
     humild
    -0.30
    íqu
    -0.29
     hidrá
    -0.29
    POSITIVE LOGITS
     extremist
    1.21
     hate
    1.14
     xen
    1.05
     racist
    1.02
     extremists
    1.01
     extremism
    1.01
    hate
    0.96
     Hate
    0.96
     hatred
    0.95
    Hate
    0.94
    Activations Density 0.811%

    No Known Activations