© 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. 11-GEMMASCOPE-RES-16K
    11. 9313
    Prev
    Next
    INDEX
    Explanations

    references to variability and differences across various dimensions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     économies
    -0.69
     yoksa
    -0.60
     bénéfices
    -0.57
     investissements
    -0.55
     dégâts
    -0.55
     maso
    -0.54
     doppia
    -0.54
    leyin
    -0.53
    нина
    -0.52
     superiori
    -0.52
    POSITIVE LOGITS
     different
    1.26
     varying
    1.05
     unterschiedlich
    1.05
    different
    1.02
     various
    0.98
    Different
    0.95
     unterschied
    0.93
     varied
    0.92
     verschieden
    0.91
     variously
    0.90
    Activations Density 0.430%

    No Known Activations