© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9810
    Prev
    Next
    INDEX
    Explanations

    phrases involving the particle "を" that indicate actions directed at objects or subjects

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

    Japanese words or phrases followed by particles

    np_acts-logits-general · gemini-2.0-flash

    death wishes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    が集
    -0.39
    が取
    -0.38
    httphttps
    -0.37
     такая
    -0.37
    がい
    -0.35
    がか
    -0.34
    Tx
    -0.33
     Mackey
    -0.32
    が残
    -0.32
     какая
    -0.31
    POSITIVE LOGITS
    りを
    0.75
    感を
    0.73
    기를
    0.73
    数を
    0.71
    리를
    0.69
    日を
    0.69
    devamını
    0.68
     را
    0.68
    体を
    0.68
    さんを
    0.68
    Activations Density 0.150%

    No Known Activations