© 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. 16274
    Prev
    Next
    INDEX
    Explanations

    HTML and script tags in web development contexts

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

    JavaScript code and related file extensions

    np_acts-logits-general · gemini-2.0-flash

    javascript scripts

    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
     runs
    -0.47
     preghiera
    -0.44
     ran
    -0.43
    Bly
    -0.42
    زه
    -0.42
    SPONSORED
    -0.40
     hran
    -0.40
     drapeau
    -0.39
    ędzy
    -0.39
    toHexString
    -0.39
    POSITIVE LOGITS
     js
    1.09
     scripts
    1.05
     script
    1.02
     javascript
    1.02
     JS
    1.01
    script
    1.00
     JavaScript
    1.00
     Scripts
    0.98
     Script
    0.97
     Javascript
    0.95
    Activations Density 0.528%

    No Known Activations