© 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. 39-GEMMASCOPE-RES-16K
    11. 2706
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs, specifically in relation to JavaScript and PHP coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lüğ
    -0.63
     œil
    -0.59
     jouet
    -0.56
     tuyau
    -0.52
     boîtier
    -0.51
     oeil
    -0.50
    før
    -0.50
     vêtement
    -0.48
     pistolet
    -0.48
     idéia
    -0.47
    POSITIVE LOGITS
     queſta
    0.73
    
    0.66
     $_"
    0.62
     Efq
    0.62
     bluzka
    0.62
     Monfieur
    0.61
     للاسماء
    0.60
     abstrato
    0.59
     tirage
    0.59
     Geſ
    0.58
    Activations Density 0.171%

    No Known Activations