© 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. 14641
    Prev
    Next
    INDEX
    Explanations

    numerical values and their context in the text

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

    Numbers within a range

    np_acts-logits-general · gemini-2.0-flash

    thousand

    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
    Хьажоргаш
    -0.80
    ⓧ
    -0.64
    Autoritní
    -0.62
     بيها
    -0.61
    MigrationBuilder
    -0.60
    EndGlobalSection
    -0.58
    CPtr
    -0.57
    PerformLayout
    -0.56
    RuleContext
    -0.55
    tagHelperRunner
    -0.54
    POSITIVE LOGITS
     thousand
    0.94
    thousand
    0.78
    Thousand
    0.72
    一千
    0.69
     Thousand
    0.68
     thousands
    0.68
     tausend
    0.67
     THOUS
    0.66
     millennium
    0.65
     Thousands
    0.64
    Activations Density 0.503%

    No Known Activations