© 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. 8918
    Prev
    Next
    INDEX
    Explanations

    instances of class and method definitions, particularly related to creating or handling data structures

    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
     disambiguazione
    -0.85
    featureID
    -0.68
     EconPapers
    -0.66
    uxxxx
    -0.64
    matchCondition
    -0.62
    URLException
    -0.59
     supervivencia
    -0.59
     Wiktionnaire
    -0.59
     dictadura
    -0.58
     يتيمه
    -0.57
    POSITIVE LOGITS
    ();
    0.53
    (){
    0.53
    []{
    0.50
    <>(
    0.50
     implements
    0.49
    Impl
    0.48
    ()
    0.47
     constructed
    0.47
     constructor
    0.46
     whose
    0.46
    Activations Density 0.163%

    No Known Activations