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. 13-GEMMASCOPE-RES-16K
    6. 7754
    Prev
    Next
    INDEX
    Explanations

    various programming and coding elements, specifically related to web development and JavaScript functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     QWidget
    -0.55
    kent
    -0.55
     StringField
    -0.51
    amqp
    -0.51
    QWidget
    -0.50
     MNRAS
    -0.49
    CharField
    -0.49
     Sanford
    -0.49
     asientos
    -0.48
    vability
    -0.46
    POSITIVE LOGITS
     NSCoder
    0.91
    UrlResolution
    0.89
    出版年
    0.88
    RenderAtEndOf
    0.86
    +#+#
    0.78
     تضيفلها
    0.76
     ujednoznacz
    0.76
    มาะ
    0.76
    DockStyle
    0.75
    الحياه
    0.74
    Activations Density 0.005%

    No Known Activations