© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 11658
    Prev
    Next
    INDEX
    Explanations

    code snippets related to date and time manipulation in programming

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

    date and time manipulation code in programming languages.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    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
    ISupport
    -0.43
    Conseil
    -0.27
    Abitanti
    -0.26
     vastaan
    -0.26
    젓
    -0.26
     risco
    -0.26
     mahdol
    -0.26
     ujednoznacz
    -0.26
    äden
    -0.26
     abandonado
    -0.26
    POSITIVE LOGITS
     date
    1.79
     dates
    1.77
     Dates
    1.59
     Date
    1.59
     DateTime
    1.51
     DATE
    1.51
     calendar
    1.47
     datetime
    1.44
    date
    1.40
    Date
    1.39
    Activations Density 0.707%

    No Known Activations