© 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. 8807
    Prev
    Next
    INDEX
    Explanations

    references to illegal immigration and related criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ðsíða
    -0.91
     myſelf
    -0.91
    majánló
    -0.87
     Infór
    -0.85
     hadas
    -0.83
     Houſe
    -0.81
     Milán
    -0.81
     Moscú
    -0.78
     Theſe
    -0.78
     ſind
    -0.76
    POSITIVE LOGITS
     Mexican
    1.25
     Mexico
    1.11
     Latin
    1.10
    Mexican
    1.03
     Мекси
    0.94
    Mexico
    0.91
    墨西哥
    0.90
    Latin
    0.88
     Mexicans
    0.88
     mexican
    0.84
    Activations Density 0.983%

    No Known Activations