© 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. 20-GEMMASCOPE-RES-16K
    11. 1339
    Prev
    Next
    INDEX
    Explanations

    numerical values and parameters related to processes in a technical context

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

    Tokens followed by a number

    np_acts-logits-general · gemini-2.0-flash

    numbers, citations, technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.51
    ViewById
    -0.48
     even
    -0.47
     filhos
    -0.42
    帖最后由
    -0.42
     phosph
    -0.41
     edel
    -0.40
    hie
    -0.40
     ../../
    -0.40
    alu
    -0.39
    POSITIVE LOGITS
    MigrationBuilder
    0.83
     AssemblyProduct
    0.78
    SourceChecksum
    0.76
     InputDecoration
    0.70
    adaptiveStyles
    0.69
     Италијани
    0.69
     utafitiHapana
    0.68
    HasAnnotation
    0.68
     '\\;'
    0.67
     بيها
    0.66
    Activations Density 0.206%

    No Known Activations