© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 4619
    Prev
    Next
    INDEX
    Explanations

    code-related terms and error messages within programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tjen
    -0.39
      
    -0.37
    ↵
    -0.36
        
    -0.33
     ulike
    -0.33
     skolen
    -0.32
     memen
    -0.32
     gärna
    -0.31
    føl
    -0.31
     going
    -0.30
    POSITIVE LOGITS
     للمعارف
    1.26
     EconPapers
    1.23
     disambiguazione
    1.10
    parsedMessage
    1.09
    featureID
    1.09
    InjectAttribute
    1.07
    AndEndTag
    1.06
     للاسماء
    1.01
    IntoConstraints
    0.97
    [@BOS@]
    0.96
    Activations Density 0.438%

    No Known Activations