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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 5753
    Prev
    Next
    INDEX
    Explanations

    code elements and syntax in programming-related text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.39
    bsch
    -0.35
    </tfoot>
    -0.34
    IBOutlet
    -0.33
     otomatig
    -0.31
    cinogen
    -0.30
    ずみ
    -0.30
    bentukan
    -0.30
    tagHelperRunner
    -0.29
    جار
    -0.28
    POSITIVE LOGITS
     reverse
    3.22
     reversed
    3.02
     Reverse
    2.84
    reverse
    2.73
     reverses
    2.70
    Reverse
    2.69
     reversing
    2.69
     reversal
    2.61
     inverse
    2.52
     revers
    2.47
    Activations Density 2.112%

    No Known Activations