© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 81307
    Prev
    Next
    INDEX
    Explanations

    conditions and exceptions in programming contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    publickey, keyboard-interactive

    np_acts-logits-general · gemini-2.5-flash-lite

    the neuron detects hedging or uncertain expressions (first-person epistemic phrases like "I guess", "I think", "maybe"/"..." and similar tentative replies).

    oai_token-act-pair · gpt-5-mini
    Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    enzio
    -0.35
     payé
    -0.32
     Einsch
    -0.32
     incendie
    -0.32
    पया
    -0.32
    quini
    -0.31
    ốc
    -0.31
     GlobalKey
    -0.31
    ansch
    -0.31
    Rien
    -0.31
    POSITIVE LOGITS
     Allowed
    0.60
    MigrationBuilder
    0.59
    Życiorys
    0.59
     allowed
    0.57
    allowed
    0.56
    oneofs
    0.56
    wapV
    0.56
    Tikang
    0.56
    complexContent
    0.53
     possibility
    0.52
    Activations Density 0.299%

    No Known Activations