© 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. 322
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connecting phrases that imply relationships between ideas

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

    the conjunction "and" in various contexts

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

    enumeration and listing

    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
     سكانية
    -0.78
    TypedDataSet
    -0.77
     дописавши
    -0.72
    '}>
    -0.71
    ----</
    -0.70
    Datuak
    -0.70
    -------------</
    -0.70
    )$}
    -0.70
    </h3>
    -0.67
    figsize
    -0.65
    POSITIVE LOGITS
    another
    0.80
     another
    0.79
     همچنین
    0.78
     Another
    0.74
     secondly
    0.74
    Another
    0.73
     außerdem
    0.71
    Others
    0.65
     infine
    0.64
     lastly
    0.63
    Activations Density 0.242%

    No Known Activations