© 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 - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 12967
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements and their structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .*")]
    -0.81
     Infórmanos
    -0.70
     AssemblyTitle
    -0.67
    yntaxException
    -0.59
    endregion
    -0.57
     jsPsych
    -0.56
    ValueGeneration
    -0.54
    +:+
    -0.52
     LoggerFactory
    -0.50
    WebServlet
    -0.50
    POSITIVE LOGITS
    tagHelperRunner
    0.56
    ValueStyle
    0.55
    RegressionTest
    0.49
     للمعارف
    0.47
     resourceCulture
    0.43
    uxxxx
    0.42
    localctx
    0.41
    adaptiveStyles
    0.41
    bitField
    0.41
    :✨
    0.39
    Activations Density 2.710%

    No Known Activations