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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9030
    Prev
    Next
    INDEX
    Explanations

    words related to scientific terms and references

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

    The neuron activates for non-English surnames and foreign person names, particularly from Eastern European, Asian, and Nordic regions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     мәкалә
    -0.61
    ViewFeatures
    -0.53
    oa̍t
    -0.49
     ModelExpression
    -0.48
    WebVitals
    -0.46
     فريبيس
    -0.46
     ligiloj
    -0.45
    Viitteet
    -0.45
     insuffisamment
    -0.44
     Мексичка
    -0.43
    POSITIVE LOGITS
    transQ
    0.60
     queſta
    0.56
    tvguidetime
    0.54
    mybatisplus
    0.52
     unſ
    0.51
    sstream
    0.50
    ontal
    0.49
    amento
    0.49
    potranspiration
    0.49
    oulou
    0.48
    Activations Density 0.847%

    No Known Activations