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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 7371
    Prev
    Next
    INDEX
    Explanations

    references to image and UI elements related to image processing and display in code

    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
    Diwedd
    -0.70
     Chwiliwch
    -0.63
    IMPORTED
    -0.62
    verifyException
    -0.59
    XmlAccessType
    -0.57
    出版年
    -0.56
    kloped
    -0.48
    PathParam
    -0.47
     bos
    -0.46
    itemBuilder
    -0.46
    POSITIVE LOGITS
     UIImage
    1.79
     UIKit
    1.73
     UIColor
    1.64
    UIImage
    1.61
    UIColor
    1.45
     CGPoint
    1.44
    UITableView
    1.43
     CGRect
    1.38
     UIView
    1.35
    UIFont
    1.33
    Activations Density 0.033%

    No Known Activations