© 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-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15241
    Prev
    Next
    INDEX
    Explanations

    the particle "を" indicating objects or direct objects in Japanese sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.92
     Jefus
    -0.89
     houſe
    -0.87
     reaſon
    -0.84
     Efq
    -0.82
     Chriftian
    -0.81
     purpoſe
    -0.80
     iſt
    -0.79
     habet
    -0.78
     ſche
    -0.77
    POSITIVE LOGITS
    を
    0.93
    曲を
    0.89
    いを
    0.86
    みを
    0.85
    子を
    0.83
    日を
    0.81
    riwal
    0.79
    을
    0.77
     CYTHON
    0.77
    さんを
    0.75
    Activations Density 0.087%

    No Known Activations