© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3495
    Prev
    Next
    INDEX
    Explanations

    complex programming constructs and structures

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

    mechanical hardness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     ujednoznacz
    -0.85
     تضيفلها
    -0.80
    TintMode
    -0.78
     Roskov
    -0.78
    RenderAtEndOf
    -0.77
     مشين
    -0.76
     */
    -0.76
    usermodel
    -0.76
    JvmStatic
    -0.75
     فريبيس
    -0.73
    POSITIVE LOGITS
        
    0.57
    •
    0.52
    +
    0.51
       
    0.49
    к
    0.49
    Xaml
    0.48
         
    0.48
    `
    0.48
    .
    0.47
    ->
    0.47
    Activations Density 0.009%

    No Known Activations