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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 925
    Prev
    Next
    INDEX
    Explanations

    terms related to financial investments and interactions

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

    proper nouns and technical terms, especially names of companies, organizations, people, brands, or specialized functions.

    oai_token-act-pair · gpt-4.1-2025-04-14Triggered by @ywhp2c8tjm

    words that seem related to business or finance.

    oai_token-act-pair · gemini-2.0-flashTriggered by @ywhp2c8tjm

    before actions or transformations

    np_acts-logits-general · gemini-2.0-flash

    actions and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     itemId
    -0.73
     deviceId
    -0.69
     pageNo
    -0.69
     statusCode
    -0.69
     newItem
    -0.66
     Nymp
    -0.66
     newUser
    -0.65
     Amic
    -0.61
     maxSize
    -0.61
     currentNode
    -0.61
    POSITIVE LOGITS
    Bind
    0.52
     meurt
    0.50
    write
    0.50
    bind
    0.49
    点此举报
    0.49
     vieill
    0.49
    send
    0.48
    apply
    0.48
     Descubre
    0.47
     Seleccione
    0.47
    Activations Density 1.043%

    No Known Activations