© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16313
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to web element manipulation in programming, particularly in web automation scripts.

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

    HTML code snippets containing specific elements and attributes.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    programming-related syntax and commands, particularly for web development and testing. It activates strongly for terms like "findElement", "XPath", "using", "element", "locator", and other code-related concepts.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Code-related terms (CSS, XPath, jQuery)

    np_acts-logits-general · gemini-2.0-flash

    locating web elements by text

    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
    DeleteBehavior
    -0.89
    rungsseite
    -0.82
    Personendaten
    -0.80
    protoimpl
    -0.80
     Италијани
    -0.79
    EDEFAULT
    -0.79
    脚注の使い方
    -0.77
     protoimpl
    -0.75
     estekak
    -0.72
    Życiorys
    -0.71
    POSITIVE LOGITS
    css
    0.61
    Css
    0.54
     yarış
    0.50
    xpath
    0.50
     xpath
    0.47
    CSS
    0.47
    id
    0.47
    ByExample
    0.46
    XPath
    0.44
     scuole
    0.44
    Activations Density 0.090%

    No Known Activations