© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12125
    Prev
    Next
    INDEX
    Explanations

    phrases related to patient care, appointments, and health consultations

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

    Scheduling or visiting a doctor

    np_acts-logits-general · gemini-2.0-flash

    medical appointments

    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
    
    -0.67
     Италијани
    -0.66
    WaitGroup
    -0.60
    PreferredItem
    -0.59
    ತಿ
    -0.58
    writeFieldEnd
    -0.58
     EconPapers
    -0.57
    /*++
    -0.57
     Signalez
    -0.57
    tvguidetime
    -0.55
    POSITIVE LOGITS
     appointments
    1.74
     appointment
    1.73
     Appointments
    1.53
     Appointment
    1.50
    Appointments
    1.47
    Appointment
    1.45
    appointments
    1.38
    appointment
    1.37
     APPOINT
    1.36
     appoint
    1.06
    Activations Density 0.259%

    No Known Activations