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. 10285
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols related to algebraic structures

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

    Mathematical expressions with symbols

    np_acts-logits-general · gemini-2.0-flash

    element or elements

    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
    RuleContext
    -0.50
    fillType
    -0.50
     getItemCount
    -0.48
    striped
    -0.46
    variants
    -0.46
     vines
    -0.46
    ArgumentParser
    -0.45
    ftagPool
    -0.45
     размер
    -0.44
    RetentionPolicy
    -0.44
    POSITIVE LOGITS
    Personendaten
    0.91
    AndEndTag
    0.75
     element
    0.74
     Element
    0.71
     ELEMENT
    0.69
    element
    0.69
     élément
    0.68
     AssemblyCulture
    0.67
     Elements
    0.66
    Personensuche
    0.66
    Activations Density 1.548%

    No Known Activations