© 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. 13-GEMMASCOPE-RES-16K
    11. 11421
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to regression analysis and diagnostics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Rho
    -0.34
    AGE
    -0.32
     Su
    -0.31
    VEN
    -0.31
     proceeds
    -0.30
     R
    -0.30
     SD
    -0.30
     Hal
    -0.30
     TR
    -0.29
     SH
    -0.29
    POSITIVE LOGITS
    uxxxx
    0.95
    GEBURTSDATUM
    0.88
    SourceChecksum
    0.83
    MessageOf
    0.70
    évaluateur
    0.70
    艋
    0.68
    OOTDTY
    0.68
    InstrumentedTest
    0.66
     CreateTagHelper
    0.66
    contentLoaded
    0.65
    Activations Density 2.368%

    No Known Activations