© 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-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 8778
    Prev
    Next
    INDEX
    Explanations

    expressions of embarrassment and shame

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     ExecuteAsync
    -0.57
    migrationBuilder
    -0.57
    mybatisplus
    -0.57
    enido
    -0.50
     transférez
    -0.50
    érale
    -0.49
    viewBox
    -0.48
    NetworkInfo
    -0.48
    Przypisy
    -0.48
     kekerasan
    -0.47
    POSITIVE LOGITS
     embarrassment
    1.79
     shame
    1.78
     embarrassed
    1.59
     ashamed
    1.55
    shame
    1.55
     Shame
    1.50
     humiliation
    1.49
     embarrassing
    1.47
     honte
    1.43
    Shame
    1.42
    Activations Density 0.233%

    No Known Activations