© 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. 100997
    Prev
    Next
    INDEX
    Explanations

    programming terminology and concepts related to query processing

    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
     pleaſure
    -0.62
     itſelf
    -0.62
    ParallelGroup
    -0.60
    Tikang
    -0.60
     ſich
    -0.60
     Majefty
    -0.60
     ſever
    -0.60
     ſeinen
    -0.60
     purpoſe
    -0.59
     ſtre
    -0.59
    POSITIVE LOGITS
    ANTLR
    0.74
    localctx
    0.66
    antlr
    0.64
    RuleContext
    0.57
    errHandler
    0.56
    ParseTree
    0.47
    CharStream
    0.47
    exitRule
    0.46
    LogFactory
    0.39
     invokingState
    0.38
    Activations Density 0.003%

    No Known Activations