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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1086
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas and parentheses

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

    punctuation marks and structure in legal or formal text

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

    list separators and conjunctions

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    elemField
    -0.76
    RegressionTest
    -0.74
     lenker
    -0.69
    ParallelGroup
    -0.69
     estekak
    -0.62
     kasarigan
    -0.61
    ThroughAttribute
    -0.59
     ddelweddau
    -0.57
    ighed
    -0.57
     henvisninger
    -0.57
    POSITIVE LOGITS
     we
    1.48
     there
    1.43
     they
    1.33
     فإن
    1.17
     it
    1.07
    there
    1.01
     you
    1.01
     они
    0.99
    they
    0.93
     она
    0.92
    Activations Density 0.259%

    No Known Activations