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. 5-GEMMASCOPE-RES-16K
    6. 14254
    Prev
    Next
    INDEX
    Explanations

    references to date and time data types and related functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.78
    phazard
    -0.76
     <=",
    -0.64
     Vele
    -0.62
     Zol
    -0.61
     Nowhere
    -0.60
     Rheinland
    -0.59
     BURN
    -0.59
    ughty
    -0.58
    ائمة
    -0.58
    POSITIVE LOGITS
     Date
    1.63
    Date
    1.62
     DATE
    1.09
     date
    1.00
    getDate
    0.92
    date
    0.91
    DATE
    0.91
     Dates
    0.87
    DateUtils
    0.79
    setDate
    0.79
    Activations Density 0.043%

    No Known Activations