© 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. 11583
    Prev
    Next
    INDEX
    Explanations

    information related to injuries and illnesses affecting individuals in various contexts

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

    Preceding words of sickness or injury

    np_acts-logits-general · gemini-2.0-flash

    illness and injury

    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
    UserScript
    -0.56
    postsleuth
    -0.54
     preuves
    -0.48
     samfun
    -0.48
     kvinder
    -0.47
     normaux
    -0.46
     åp
    -0.46
     DataTypes
    -0.46
    +#+#
    -0.45
     graisse
    -0.45
    POSITIVE LOGITS
     illness
    2.06
     sickness
    1.88
     sick
    1.84
     illnesses
    1.77
     Illness
    1.75
     injured
    1.66
    sick
    1.58
     injury
    1.57
     injuries
    1.56
     unwell
    1.53
    Activations Density 0.711%

    No Known Activations