© 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. 16232
    Prev
    Next
    INDEX
    Explanations

    elements of structured data or lists in a technical context

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

    Characters inside parentheses

    np_acts-logits-general · gemini-2.0-flash

    graph/diagram nodes (A, B, C, D, E)

    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
    __(/*!
    -0.69
     cucchia
    -0.54
     propOrder
    -0.53
     feltro
    -0.53
     épaules
    -0.50
     bicchiere
    -0.49
     hauts
    -0.48
    ärsk
    -0.48
    wakili
    -0.47
    DropTable
    -0.47
    POSITIVE LOGITS
     S
    0.78
    webElementXpaths
    0.78
     P
    0.73
     EconPapers
    0.71
     R
    0.71
     G
    0.67
    MENAFN
    0.67
     T
    0.67
     L
    0.67
     C
    0.66
    Activations Density 1.342%

    No Known Activations