© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 10405
    Prev
    Next
    INDEX
    Explanations

    instances of the particle "を" used in various grammatical structures in Japanese

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -0.82
     purpoſe
    -0.81
     Jefus
    -0.78
     reaſon
    -0.78
     sonne
    -0.75
    ✭✭
    -0.74
     pleaſure
    -0.74
     ſche
    -0.73
     Chriftian
    -0.70
     reafon
    -0.69
    POSITIVE LOGITS
    を
    1.58
    을
    1.37
    를
    1.29
    曲を
    1.17
     を
    1.14
    子を
    1.13
     를
    1.12
     을
    1.11
    さんを
    1.05
    いを
    1.04
    Activations Density 0.021%

    No Known Activations