© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11556
    Prev
    Next
    INDEX
    Explanations

    programming constructs such as commands and control flow statements

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

    "case" or code snippets containing "case"

    np_acts-logits-general · gemini-2.0-flash

    case and products in

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    SourceChecksum
    -0.58
    migrationBuilder
    -0.58
    SizeMode
    -0.57
    DockStyle
    -0.56
    LayoutStyle
    -0.54
    kmale
    -0.54
    ismus
    -0.53
    Geplaatst
    -0.50
     AssemblyCulture
    -0.47
    adaptiveStyles
    -0.45
    POSITIVE LOGITS
    case
    0.74
     case
    0.70
    Case
    0.61
    
    0.60
     дописавши
    0.57
     ivelany
    0.57
    izr
    0.56
    awtextra
    0.53
    yonel
    0.53
    сылкі
    0.53
    Activations Density 0.095%

    No Known Activations