© 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. 23-GEMMASCOPE-RES-16K
    11. 6424
    Prev
    Next
    INDEX
    Explanations

    words related to spatial relationships and locations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     also
    -0.35
    platte
    -0.31
     "__
    -0.31
    Commonwealth
    -0.30
    fi
    -0.29
     Commonwealth
    -0.28
     time
    -0.27
     fully
    -0.27
     included
    -0.27
     likewise
    -0.27
    POSITIVE LOGITS
    UrlResolution
    0.83
     initComponents
    0.73
     ویکی‌پدی
    0.71
     Савезне
    0.70
     ligiloj
    0.70
     Geſch
    0.70
     >=",
    0.67
    principalTable
    0.66
     cherchés
    0.66
    tagext
    0.66
    Activations Density 0.477%

    No Known Activations