© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 13406
    Prev
    Next
    INDEX
    Explanations

    references to correcting mistakes or errors

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

    "correct" or its variations

    np_acts-logits-general · gemini-2.0-flash

    correcting and accuracy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     `/
    -0.52
    VersionUID
    -0.47
     Â
    -0.47
     â
    -0.46
    />
    -0.45
     Huston
    -0.44
    ={`
    -0.44
    onMouse
    -0.44
    Â
    -0.44
     spa
    -0.43
    POSITIVE LOGITS
     Correct
    1.84
     correct
    1.80
    Correct
    1.77
    correct
    1.77
     CORRECT
    1.58
    CORRECT
    1.52
     corrects
    1.48
     correc
    1.42
     correction
    1.41
     corrected
    1.40
    Activations Density 0.233%

    No Known Activations