© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7643
    Prev
    Next
    INDEX
    Explanations

    date and time formatting elements in code

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

    Deals with dates and times

    np_acts-logits-general · gemini-2.0-flash

    date parsing and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    גות
    -0.43
     choirs
    -0.43
    tagHelperRunner
    -0.43
    exitRule
    -0.42
    BASEPATH
    -0.42
    reid
    -0.42
     pew
    -0.40
    ffindor
    -0.40
    pew
    -0.39
    ueil
    -0.39
    POSITIVE LOGITS
     date
    1.74
     dates
    1.65
     Date
    1.60
     DATE
    1.55
     Dates
    1.54
    date
    1.50
    Date
    1.47
     days
    1.39
    dates
    1.37
    Dates
    1.37
    Activations Density 0.543%

    No Known Activations