© 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. 1-GEMMASCOPE-RES-16K
    11. 10338
    Prev
    Next
    INDEX
    Explanations

    the word "は" (wa), a particle frequently used in the Japanese language to indicate the topic of a sentence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.94
    RenderAtEndOf
    -0.82
     bezeichneter
    -0.77
     BoxFit
    -0.68
    usercontent
    -0.67
    ksikon
    -0.67
     Roskov
    -0.66
     jsPsych
    -0.66
    LLocation
    -0.65
     Wikimedijinoj
    -0.64
    POSITIVE LOGITS
    は
    2.31
    은
    1.94
    는
    1.86
     は
    1.62
    は無
    1.25
     는
    1.23
    いは
    1.20
    りは
    1.19
    性は
    1.19
    には
    1.19
    Activations Density 0.029%

    No Known Activations