© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1572
    Prev
    Next
    INDEX
    Explanations

    phrases relating to consequences and potential outcomes

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

    instances of financial implications and their consequences related to governmental actions

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

    predicting common continuations

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    Geplaatst
    -1.37
     kasarigan
    -1.36
    Билгалдахарш
    -1.35
     Majefty
    -1.32
     purpoſe
    -1.31
     myſelf
    -1.29
     Jefus
    -1.29
    parsedMessage
    -1.28
     propOrder
    -1.28
     дописавши
    -1.27
    POSITIVE LOGITS
     
    0.85
     (
    0.78
    ,
    0.71
     a
    0.70
    -
    0.69
    .
    0.67
     “
    0.67
     in
    0.63
     "
    0.62
     -
    0.62
    Activations Density 2.475%

    No Known Activations