© 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. 31-GEMMASCOPE-RES-16K
    11. 12073
    Prev
    Next
    INDEX
    Explanations

    references to historical figures or events related to Japanese leaders and political periods

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

    Japanese names and locations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    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
    -0.36
    didSet
    -0.34
     Tho
    -0.33
    ‗
    -0.32
    invokeLater
    -0.32
    廷
    -0.31
     veta
    -0.31
     Madi
    -0.30
    حوالہ
    -0.30
     zim
    -0.29
    POSITIVE LOGITS
     Japan
    1.23
     Japón
    1.16
     Jepang
    1.15
    Japan
    1.13
     Japanese
    1.13
     japan
    1.02
    ญี่ปุ่น
    1.00
     Giappone
    1.00
     Japão
    0.99
     JAPAN
    0.98
    Activations Density 1.148%

    No Known Activations