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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 14959
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and elements related to coding and automation

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

    Selenium/WebDriver code and errors

    np_acts-logits-general · gemini-2.0-flash

    locate element selenium webdriver

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemLayout
    -0.70
     الرخصة
    -0.66
    roek
    -0.66
     simplifié
    -0.65
    KommentareTeilen
    -0.62
     planes
    -0.62
     FishBase
    -0.61
    ToBounds
    -0.61
    antism
    -0.60
    PMailer
    -0.60
    POSITIVE LOGITS
    openqa
    0.77
    webdriver
    0.73
    WebElementEntity
    0.72
    selenium
    0.69
     webdriver
    0.66
    Selenium
    0.60
     selenium
    0.59
    WebElement
    0.57
     Selenium
    0.57
    WebDriver
    0.57
    Activations Density 0.063%

    No Known Activations