© 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. 105410
    Prev
    Next
    INDEX
    Explanations

    variables and parameters related to functions and data structures in programming code

    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
    SharedCtor
    -0.60
    writeFieldEnd
    -0.58
    exitRule
    -0.56
    -------------</
    -0.54
    Spolja
    -0.54
    ۜ
    -0.53
     Normdatei
    -0.52
    AndEndTag
    -0.52
    Sklici
    -0.52
    Autoritní
    -0.51
    POSITIVE LOGITS
    SpringRunner
    0.36
     []:
    0.31
    ::_('
    0.31
    Carriera
    0.30
    __":
    0.30
     Interventions
    0.30
    Uni
    0.29
    att
    0.29
    Slf
    0.28
    ガニック
    0.28
    Activations Density 0.005%

    No Known Activations