© 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. 20-GEMMASCOPE-RES-16K
    11. 3741
    Prev
    Next
    INDEX
    Explanations

    the word "を" which is a particle often used to indicate the direct object in a sentence

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

    Japanese sentences containing を

    np_acts-logits-general · gemini-2.0-flash

    actions on identity documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.63
    受け
    -0.62
    quias
    -0.62
     avoient
    -0.61
     række
    -0.61
     ordinaires
    -0.60
    見せ
    -0.60
    選ぶ
    -0.59
    行
    -0.57
     sûr
    -0.57
    POSITIVE LOGITS
    fjspx
    0.75
    ]='\
    0.74
    Begriffsklä
    0.70
    nemonic
    0.69
     nahilalakip
    0.66
    tubers
    0.64
    UNDLE
    0.63
     createSlice
    0.63
    ÚBL
    0.62
    makeText
    0.62
    Activations Density 0.031%

    No Known Activations