© 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. 30-GEMMASCOPE-RES-16K
    11. 12519
    Prev
    Next
    INDEX
    Explanations

    references to Japanese patents and related documents

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

    Japanese patent publications and numbers

    np_acts-logits-general · gemini-2.0-flash

    japanese patent references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    同
    -0.35
    numerusform
    -0.34
     bedo
    -0.34
    freopen
    -0.33
    科普
    -0.33
    先
    -0.32
    果
    -0.32
    ‗
    -0.32
    didSet
    -0.30
     Gha
    -0.30
    POSITIVE LOGITS
     Japan
    1.16
     Jepang
    1.11
    Japan
    1.10
     Japón
    1.09
     Giappone
    1.02
     Japanese
    1.01
     japan
    0.99
     Japon
    0.94
     Japão
    0.94
    ญี่ปุ่น
    0.93
    Activations Density 0.938%

    No Known Activations