© 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. 2-GEMMASCOPE-RES-16K
    11. 15595
    Prev
    Next
    INDEX
    Explanations

    occurrences of script tags in HTML documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +:+
    -0.86
    ̈́
    -0.71
    tvguidetime
    -0.67
    InSection
    -0.64
    jsxFileName
    -0.61
    tokio
    -0.59
    InputBorder
    -0.59
    下载附件
    -0.58
    )(((
    -0.58
     Monfieur
    -0.57
    POSITIVE LOGITS
    script
    3.53
    Script
    2.18
    SCRIPT
    1.99
     script
    1.99
     Script
    1.78
    cript
    1.73
     SCRIPT
    1.60
    scripts
    1.51
     scripts
    1.45
     Scripts
    1.27
    Activations Density 0.037%

    No Known Activations