© 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. 2891
    Prev
    Next
    INDEX
    Explanations

    mentions of political positions and titles within government contexts

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

    names and titles of political figures, particularly members of Congress.

    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
     propOrder
    -0.50
     المعيارى
    -0.43
    SharedCtor
    -0.42
     denken
    -0.41
     doInBackground
    -0.40
    niña
    -0.40
    ceğim
    -0.40
     subterrá
    -0.38
     gwia
    -0.38
     gustos
    -0.38
    POSITIVE LOGITS
     Speaker
    1.28
     speaker
    1.11
     House
    1.06
    Speaker
    1.02
     SPEAKER
    0.90
    House
    0.87
     Speakers
    0.85
    speaker
    0.83
    SPEAKER
    0.81
     chamber
    0.78
    Activations Density 0.340%

    No Known Activations