© 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. 10-GEMMASCOPE-RES-16K
    11. 9560
    Prev
    Next
    INDEX
    Explanations

    patterns and measurements related to medical and biological data

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    +#+#
    -1.00
     snippetHide
    -0.89
    elemField
    -0.89
     mergeFrom
    -0.87
     дописавши
    -0.86
     Roskov
    -0.86
     يتيمه
    -0.85
    SharedDtor
    -0.82
    QMetaType
    -0.82
    PerformLayout
    -0.81
    POSITIVE LOGITS
    ...
    0.51
     Old
    0.45
     régi
    0.43
     old
    0.43
     proprio
    0.42
    Old
    0.41
    old
    0.39
     vieux
    0.38
    translates
    0.38
    webf
    0.37
    Activations Density 1.270%

    No Known Activations