Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 773
    Prev
    Next
    INDEX
    Explanations

    JavaScript functions related to element manipulation in the DOM

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

    references to jQuery methods that manipulate HTML attributes

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

    HTML/DOM element selection

    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
     Monfieur
    -0.83
     $_"
    -0.81
     resourceCulture
    -0.79
     pleaſure
    -0.76
     Efq
    -0.75
    RegressionTest
    -0.75
    setVerticalGroup
    -0.75
     ―――――
    -0.74
    tvguidetime
    -0.74
     Theſe
    -0.72
    POSITIVE LOGITS
     element
    1.21
     div
    1.08
     elements
    1.06
    Element
    1.06
     DOM
    1.06
     HTML
    1.06
    element
    1.05
     Element
    1.03
     dom
    1.00
     Elements
    0.94
    Activations Density 0.957%

    No Known Activations