© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1704
    Prev
    Next
    INDEX
    Explanations

    sections of code and programming-related syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    C/C++ code: #include or if statements

    np_acts-logits-general · gemini-2.0-flash

    #if/#ifdef/#ifndef

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.72
    principalTable
    -0.71
    principalColumn
    -0.60
    Hentet
    -0.60
    styleType
    -0.59
    webElement
    -0.59
    KommentareTeilen
    -0.57
    parsedMessage
    -0.57
    şört
    -0.56
     omge
    -0.56
    POSITIVE LOGITS
    :✨
    0.46
    ADDITIONAL
    0.41
    Additional
    0.36
    Mediabestanden
    0.36
     additional
    0.35
     diligen
    0.35
    大
    0.34
     дописавши
    0.34
     ADDITIONAL
    0.33
     Dampf
    0.33
    Activations Density 0.140%

    No Known Activations