© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 9617
    Prev
    Next
    INDEX
    Explanations

    structured data formats and metadata related to document creation and updates

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

    Dates separated by slashes or dashes

    np_acts-logits-general · gemini-2.0-flash

    months and separators

    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
    IsMutable
    -0.86
    exitRule
    -0.70
    ViewImports
    -0.65
     poveznice
    -0.61
    uxxxx
    -0.61
     تضيفلها
    -0.60
    BASEPATH
    -0.59
    AddHtmlAttribute
    -0.59
     '\\;'
    -0.59
     незавершена
    -0.59
    POSITIVE LOGITS
    /
    0.86
    -
    0.67
    AUG
    0.65
    FEB
    0.62
    SEP
    0.60
    JAN
    0.57
    Mar
    0.56
    JUL
    0.56
    Dez
    0.56
    Nov
    0.56
    Activations Density 0.184%

    No Known Activations