© 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. 19-GEMMASCOPE-RES-16K
    11. 12038
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to treatments and dosage instructions

    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
    IntoConstraints
    -0.70
    chließend
    -0.54
     Wille
    -0.49
    kyo
    -0.49
     disponibilités
    -0.48
    laut
    -0.47
    WIRE
    -0.47
     Wire
    -0.47
    Wire
    -0.45
     فريبيس
    -0.45
    POSITIVE LOGITS
     administered
    0.92
     orally
    0.82
     dose
    0.78
     administration
    0.78
     doses
    0.77
     dosage
    0.77
    administered
    0.77
    dose
    0.76
     injection
    0.75
     dosages
    0.74
    Activations Density 0.827%

    No Known Activations