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. 1190
    Prev
    Next
    INDEX
    Explanations

    titles and roles related to academic positions, specifically "professor."

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

    titles and roles related to academia

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

    professor of

    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
    OGND
    -0.77
    ChildScrollView
    -0.70
    IBarButtonItem
    -0.62
     /\.(
    -0.59
    beforeAll
    -0.59
    ibatis
    -0.58
    ammans
    -0.58
    ửa
    -0.56
    ipedi
    -0.56
     Comfor
    -0.56
    POSITIVE LOGITS
    ial
    0.66
     emeritus
    0.64
    Przypisy
    0.52
    forName
    0.51
    roon
    0.51
     Emeritus
    0.50
    级
    0.49
    WriteLiteral
    0.49
    iums
    0.49
     teaching
    0.47
    Activations Density 0.007%

    No Known Activations