© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 13162
    Prev
    Next
    INDEX
    Explanations

    references to calendars and date-related concepts

    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
     MonoBehaviour
    -0.96
     ddelweddau
    -0.89
    endphp
    -0.85
    InjectAttribute
    -0.84
     HttpNotFound
    -0.81
    jooq
    -0.79
     onPostExecute
    -0.78
    PreExecute
    -0.76
    GTCX
    -0.76
    otheby
    -0.75
    POSITIVE LOGITS
     calendar
    3.29
     Calendar
    2.92
    calendar
    2.69
     calendars
    2.62
    Calendar
    2.59
     CALENDAR
    2.44
    CALENDAR
    2.08
     Calend
    2.05
     calend
    2.04
     Kalender
    2.00
    Activations Density 0.045%

    No Known Activations