© 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. 518
    Prev
    Next
    INDEX
    Explanations

    references to diseases and health conditions

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

    Infection or disease transmission

    np_acts-logits-general · gemini-2.0-flash

    pathogen transmission

    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
    •Gemma-2-2B-L20-Structure-Cluster
    Technical Natural Language (spread of disease)

    No Comments

    Negative Logits
    setCustom
    -0.50
     scomp
    -0.48
    Shr
    -0.46
    yarnpkg
    -0.46
     Shr
    -0.45
     richiesto
    -0.44
    mern
    -0.44
    ETIES
    -0.43
    öny
    -0.42
    lccn
    -0.41
    POSITIVE LOGITS
     exposure
    1.17
     contaminated
    1.09
     infect
    1.06
     contamination
    1.04
     infecting
    1.03
    contaminated
    1.03
     contact
    1.03
     contaminate
    1.00
     infected
    1.00
     transmission
    0.98
    Activations Density 0.632%

    No Known Activations