© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 628
    Prev
    Next
    INDEX
    Explanations

    references to numerical values and statistical data

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

    technical or programming-related syntax and identifiers, particularly those related to network protocols and code structures.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    mentions of numbers, especially standalone numeric identifiers in citations, sections, code/constants, and measurements (including Roman numerals and hex values)

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    numerical citations or reference markers in academic and technical documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    Inc
    -0.45
    cayaan
    -0.43
     joaat
    -0.41
    Попис
    -0.41
     Euphrates
    -0.39
    
    -0.38
    INC
    -0.36
    inc
    -0.35
     Центра
    -0.35
     zentralen
    -0.35
    POSITIVE LOGITS
    expandindo
    0.79
     disambiguazione
    0.75
     Biôgrafia
    0.75
     estekak
    0.72
    QMetaType
    0.71
     protoimpl
    0.70
     EClass
    0.69
     kaarangay
    0.68
     Photocase
    0.65
    ValueGenerated
    0.61
    Activations Density 0.490%

    No Known Activations