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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 8331
    Prev
    Next
    INDEX
    Explanations

    technical terms related to coding and web automation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.62
    transQ
    -0.52
    MemoryWarning
    -0.51
    ائرة
    -0.50
    ="<?=$
    -0.50
    تقاوى
    -0.50
     censorship
    -0.49
    ViewStyle
    -0.49
     Petty
    -0.49
    KommentareTeilen
    -0.48
    POSITIVE LOGITS
     WebDriver
    1.02
     driver
    0.98
    WebDriver
    0.97
     webdriver
    0.96
     WebElement
    0.96
     Selenium
    0.95
    driver
    0.95
    webElement
    0.94
     WebDriverWait
    0.92
    Selenium
    0.92
    Activations Density 0.174%

    No Known Activations