Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8445
    Prev
    Next
    INDEX
    Explanations

    phrases related to scheduling and managing appointments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     giuri
    -0.76
     jurado
    -0.68
     lenker
    -0.68
     ladri
    -0.66
     Schülern
    -0.66
    ntgen
    -0.65
     aDecoder
    -0.65
     juridique
    -0.64
     Krishna
    -0.64
    usda
    -0.64
    POSITIVE LOGITS
     appointment
    3.22
     appointments
    2.91
     Appointment
    2.85
     APPOINT
    2.75
    Appointment
    2.68
     Appointments
    2.67
     appoint
    2.50
    appointment
    2.48
    Appointments
    2.34
     appointed
    2.34
    Activations Density 0.056%

    No Known Activations