© 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. 3-GEMMASCOPE-RES-16K
    11. 11609
    Prev
    Next
    INDEX
    Explanations

    references to "Us" or related terms that indicate a collective identity or group

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    rix
    -0.32
     damos
    -0.31
    湃
    -0.30
    amarin
    -0.29
    egen
    -0.28
    Geographie
    -0.28
    raux
    -0.27
    ijo
    -0.27
    较大
    -0.27
     steady
    -0.26
    POSITIVE LOGITS
     Us
    2.31
    Us
    1.93
     US
    1.56
     us
    1.45
     Usa
    1.38
    US
    1.34
     usa
    1.30
    Usa
    1.30
     Usu
    1.13
     usu
    1.09
    Activations Density 0.865%

    No Known Activations