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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 11181
    Prev
    Next
    INDEX
    Explanations

    references to date and time handling functions or data types

    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
     NSCoder
    -0.85
     modelAndView
    -0.83
    uffer
    -0.83
     Elsie
    -0.82
    Autoritní
    -0.79
    onOptions
    -0.79
    NameInMap
    -0.74
    MeasureSpec
    -0.73
    
    -0.72
    devServer
    -0.70
    POSITIVE LOGITS
    DateTime
    2.73
     DateTime
    2.71
    datetime
    2.02
     datetime
    1.97
     dateTime
    1.76
    dateTime
    1.59
    DATETIME
    1.41
    DateTimeField
    1.32
    onedDateTime
    1.30
    Datetime
    1.27
    Activations Density 0.034%

    No Known Activations