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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13746
    Prev
    Next
    INDEX
    Explanations

    elements related to automation and scripting in web tasks

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

    Code-related words or tokens

    np_acts-logits-general · gemini-2.0-flash

    web scraping tools

    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
    ViewStyle
    -0.65
     testigo
    -0.48
    cristo
    -0.47
     BaseActivity
    -0.47
     lesbian
    -0.47
     cardinality
    -0.46
     vaih
    -0.46
     anteriorly
    -0.46
     pulmonar
    -0.45
    脚注の使い方
    -0.45
    POSITIVE LOGITS
     scraping
    0.99
     bot
    0.97
     Scra
    0.94
     Bot
    0.92
     scrape
    0.92
     Scrap
    0.86
     scraper
    0.84
     crawler
    0.83
     BeautifulSoup
    0.82
    scrap
    0.81
    Activations Density 0.379%

    No Known Activations