© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 25747
    Prev
    Next
    INDEX
    Explanations

    elements related to function definitions and structure within programming code

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     overseas
    -0.47
    γι
    -0.44
     local
    -0.44
     mata
    -0.44
     subsequent
    -0.44
    わけではない
    -0.43
     boyunca
    -0.43
     trusted
    -0.43
     gereken
    -0.43
     onshore
    -0.43
    POSITIVE LOGITS
    abestanden
    0.84
    Hozzáférés
    0.83
     дописавши
    0.80
    Personensuche
    0.78
     typelib
    0.77
    findpost
    0.76
    הערות
    0.72
     Roskov
    0.70
     للمعارف
    0.69
     الحره
    0.69
    Activations Density 0.001%

    No Known Activations