© 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. 3-GEMMASCOPE-RES-16K
    11. 4526
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting elements in text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Dany
    -0.76
     déc
    -0.73
    er
    -0.68
     Tuk
    -0.68
     Marcell
    -0.68
     infan
    -0.66
     Ansel
    -0.66
     GIPHY
    -0.64
     coron
    -0.64
    ното
    -0.63
    POSITIVE LOGITS
     ,
    1.21
    Datuak
    1.00
     ,,
    0.91
     mourir
    0.91
    ../../
    0.90
    Rodriguez
    0.88
     popoli
    0.87
    {{$
    0.87
     ,
    0.85
    bukaan
    0.83
    Activations Density 0.179%

    No Known Activations