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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-GEMMASCOPE-RES-16K
    6. 12821
    Prev
    Next
    INDEX
    Explanations

    symbols and expressions commonly used in programming or mathematical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vernight
    -0.85
    openqa
    -0.79
    IBarButtonItem
    -0.68
    ποίη
    -0.68
    artifactId
    -0.66
     overnight
    -0.66
    epam
    -0.65
    rrh
    -0.64
    ectl
    -0.64
    mbggenerated
    -0.64
    POSITIVE LOGITS
    ${
    1.72
    >");
    
    0.83
    ">${
    0.76
    [++
    0.72
     autorytatywna
    0.69
    Hentet
    0.69
     <<<<<<<<<<<<<<
    0.68
    TagMode
    0.67
    >");
    0.65
    WithEmail
    0.64
    Activations Density 0.013%

    No Known Activations