© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6248
    Prev
    Next
    INDEX
    Explanations

    references to health issues and illness-related scenarios

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

    being sick or ill

    np_acts-logits-general · gemini-2.0-flash

    fell ill

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DataTypes
    -0.47
    vaz
    -0.46
    áneos
    -0.45
     ElevatedButton
    -0.43
     samfun
    -0.41
     koul
    -0.41
     Counter
    -0.41
    lewati
    -0.41
     saltar
    -0.41
    lorin
    -0.41
    POSITIVE LOGITS
     illness
    2.12
     sickness
    1.97
     sick
    1.96
     Illness
    1.85
     illnesses
    1.77
     Sickness
    1.68
    sick
    1.68
     unwell
    1.66
     Sick
    1.57
    Sick
    1.56
    Activations Density 0.381%

    No Known Activations