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

    Neuronpedia

    Jacobian LensNEW
    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. 38-GEMMASCOPE-RES-16K
    11. 11190
    Prev
    Next
    INDEX
    Explanations

    instances of specific Japanese characters or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    お
    -0.83
    人
    -0.61
    お店
    -0.57
    ア
    -0.57
    大
    -0.56
    一
    -0.56
    人生
    -0.53
    人物
    -0.52
    一部
    -0.50
    话
    -0.50
    POSITIVE LOGITS
    みに
    0.68
    yntaxException
    0.66
    writeFieldEnd
    0.66
    msgTypes
    0.64
    IndentedString
    0.60
    oa̍t
    0.59
    AsUp
    0.57
    parsedMessage
    0.57
    delwed
    0.57
     AssemblyVersion
    0.56
    Activations Density 0.075%

    No Known Activations