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. 2191
    Prev
    Next
    INDEX
    Explanations

    references to individuals involved in historical conflicts and political events

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

    Years in the 1700s or 1800s

    np_acts-logits-general · gemini-2.0-flash

    XVIII, eighteenth, Napoleonic

    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
     betweenstory
    -0.76
    rungsseite
    -0.72
     Administrativna
    -0.72
    addCriterion
    -0.72
    новниш
    -0.68
     للمعارف
    -0.68
     HttpNotFound
    -0.66
    شهاد
    -0.66
    ControllerTest
    -0.65
    λευτα
    -0.64
    POSITIVE LOGITS
     Rocha
    0.51
     Revolutionary
    0.49
     Napoleonic
    0.47
     XVIII
    0.47
     Hamilton
    0.46
     Enlightenment
    0.45
     eighteenth
    0.45
     Aufklärung
    0.45
     Burr
    0.45
     Revolution
    0.44
    Activations Density 0.458%

    No Known Activations