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. 5-GEMMASCOPE-RES-16K
    6. 1837
    Prev
    Next
    INDEX
    Explanations

    elements and classes related to navigation bars in web development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     @"/
    -0.71
    XmlAccessType
    -0.65
     actionPerformed
    -0.65
    hasMoreElements
    -0.63
    +#+#
    -0.63
     متعلقه
    -0.62
     Exactos
    -0.61
     Egon
    -0.60
     XCTest
    -0.58
    writeField
    -0.58
    POSITIVE LOGITS
    navbar
    2.41
     navbar
    2.19
    Navbar
    1.72
     Navbar
    1.56
    NavBar
    0.99
     AppBar
    0.91
     NavBar
    0.86
    toolbar
    0.81
    zoll
    0.81
    AppBar
    0.77
    Activations Density 0.021%

    No Known Activations