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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16114
    Prev
    Next
    INDEX
    Explanations

    references to calendars and events in a programming context

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

    "calendar"

    np_acts-logits-general · gemini-2.0-flash

    calendar and calendar entries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     насељу
    -0.34
    MemoryWarning
    -0.31
     narkoba
    -0.31
    ⓧ
    -0.30
    ฟัง
    -0.30
     ترک
    -0.30
     braços
    -0.28
    urlencoded
    -0.28
    exit
    -0.28
     tirantes
    -0.28
    POSITIVE LOGITS
     calendar
    2.19
     calendars
    1.94
     Calendar
    1.92
     CALENDAR
    1.74
     calendario
    1.73
     Calend
    1.70
    calendar
    1.68
    Calendar
    1.64
     calend
    1.63
     calendrier
    1.59
    Activations Density 0.152%

    No Known Activations