© 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. 37-GEMMASCOPE-RES-16K
    11. 9115
    Prev
    Next
    INDEX
    Explanations

    repeated prefixes in words and phrases

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     replacement
    -0.38
     tromper
    -0.33
     Zusatz
    -0.33
     finally
    -0.33
     Replacement
    -0.32
    förm
    -0.31
     arrière
    -0.31
     bantuan
    -0.30
    Obrázky
    -0.30
     enhancement
    -0.29
    POSITIVE LOGITS
    InputBorder
    0.61
    inflate
    0.59
    vamp
    0.58
    Vamp
    0.57
     ویکی‌پدی
    0.57
    MLLoader
    0.56
    makeConstraints
    0.56
     Taktlose
    0.55
    configure
    0.54
    familiar
    0.54
    Activations Density 0.288%

    No Known Activations