© 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. 18-GEMMASCOPE-RES-16K
    11. 9329
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare providers and patients

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

    Roles: caregiver, teacher, provider, driver, patient, investor

    np_acts-logits-general · gemini-2.0-flash

    roles in surveys and training

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.83
    IntoConstraints
    -0.68
    AndEndTag
    -0.67
     تضيفلها
    -0.66
    XmlAccessType
    -0.63
    ConstraintMaker
    -0.63
    PerformLayout
    -0.63
    URLException
    -0.62
     épis
    -0.62
    transQ
    -0.61
    POSITIVE LOGITS
     participation
    0.70
     involvement
    0.64
    --){
    0.61
     engagement
    0.60
     who
    0.60
     input
    0.58
     feedback
    0.57
     opinion
    0.56
    们的
    0.54
     relations
    0.53
    Activations Density 0.395%

    No Known Activations