© 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. 2-GEMMASCOPE-RES-16K
    6. 8574
    Prev
    Next
    INDEX
    Explanations

    terms related to illness and health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PagerAdapter
    -0.67
    oneofs
    -0.65
     insi
    -0.65
    insee
    -0.61
     estekak
    -0.61
     mergeFrom
    -0.60
    eloma
    -0.58
    awaiter
    -0.58
    ništ
    -0.57
    enumi
    -0.56
    POSITIVE LOGITS
     illness
    1.20
     Illness
    1.08
     illnesses
    1.03
     ill
    0.99
     Ill
    0.92
     sick
    0.92
    Ill
    0.90
    ill
    0.79
     sickness
    0.78
    Sick
    0.77
    Activations Density 0.034%

    No Known Activations