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

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2689
    Prev
    Next
    INDEX
    Explanations

    coding and programming-related elements, specifically in API and web development contexts

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

    autorest.As functions in Go code

    np_acts-logits-general · gemini-2.0-flash

    API preparer and UI alloc

    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
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.93
     للاسماء
    -0.91
    awtextra
    -0.84
    #![
    -0.82
    ⓧ
    -0.82
     الحره
    -0.81
    RegressionTest
    -0.80
     NSCoder
    -0.79
    
    -0.79
    AnimationsModule
    -0.78
    POSITIVE LOGITS
    uxxxx
    0.37
     ting
    0.37
     par
    0.35
     pr
    0.35
     p
    0.35
     pro
    0.34
     j
    0.34
     lat
    0.33
     ka
    0.33
     parti
    0.33
    Activations Density 0.076%

    No Known Activations