© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 10601
    Prev
    Next
    INDEX
    Explanations

    references to Japan and its geopolitical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assurer
    -0.40
    accro
    -0.38
    %(
    -0.37
    AZIONI
    -0.37
     communiquer
    -0.35
    taylor
    -0.35
    الحياه
    -0.35
     maaaring
    -0.34
    คิด
    -0.34
     Mal
    -0.34
    POSITIVE LOGITS
     Japan
    0.90
    Japan
    0.89
     japan
    0.88
     Japón
    0.82
     Jepang
    0.78
     Japanese
    0.75
     Giappone
    0.74
     Japon
    0.72
    Japanese
    0.71
     japanese
    0.71
    Activations Density 0.717%

    No Known Activations