© 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. 19-GEMMASCOPE-RES-16K
    6. 5562
    Prev
    Next
    INDEX
    Explanations

    French prepositions, with a specific focus on the word "de."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.81
     himſelf
    -0.77
     Majefty
    -0.74
     Jefus
    -0.74
     Cæsar
    -0.74
     Chriftian
    -0.73
     raiſ
    -0.71
     Efq
    -0.68
     hamilton
    -0.68
    UnitTesting
    -0.66
    POSITIVE LOGITS
     the
    0.79
     an
    0.71
     course
    0.69
    course
    0.66
    COURSE
    0.64
    '>
    
    0.59
    udz
    0.58
    letus
    0.58
     la
    0.58
    leta
    0.57
    Activations Density 0.028%

    No Known Activations