© 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. 3-GEMMASCOPE-RES-16K
    11. 9689
    Prev
    Next
    INDEX
    Explanations

    sequences of underscores or blank spaces within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.86
    parsedMessage
    -0.78
    脚注の使い方
    -0.78
    Дереккөздер
    -0.75
    таратура
    -0.74
    tagHelperRunner
    -0.74
     okuyayım
    -0.71
    Autoritní
    -0.70
    rungsseite
    -0.69
     ModelExpression
    -0.68
    POSITIVE LOGITS
     hers
    0.49
    num
    0.48
    usermodel
    0.48
    .
    0.46
     rocz
    0.45
     affatto
    0.44
     Abteilung
    0.44
     cavo
    0.43
    <>("
    0.43
     issuing
    0.43
    Activations Density 1.356%

    No Known Activations