© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104992
    Prev
    Next
    INDEX
    Explanations

    occurrences of variables and identifiers in code related to data structures or mathematical constructs

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     الحره
    -0.88
    parsedMessage
    -0.75
     للاسماء
    -0.74
    AddTagHelper
    -0.69
    новниш
    -0.64
    MigrationBuilder
    -0.62
     Taktlose
    -0.62
     estekak
    -0.60
    Autoritní
    -0.60
    oredCriteria
    -0.60
    POSITIVE LOGITS
    _
    0.44
    :
    0.44
     
    0.42
    0.41
     expanse
    0.41
     surface
    0.40
     domain
    0.40
    "
    0.39
     element
    0.38
     aspect
    0.38
    Activations Density 0.001%
    No Known Activations