© 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. 1923
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate certainty or emphasis

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

    adverbs qualifying actions

    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
     fouling
    -0.64
     serem
    -0.62
     realisation
    -0.61
     Diſ
    -0.57
     perfons
    -0.56
     ſon
    -0.56
     ſeveral
    -0.56
     stabilisation
    -0.56
     spotting
    -0.56
     Chriſt
    -0.55
    POSITIVE LOGITS
     had
    1.03
     got
    0.96
     took
    0.94
     began
    0.92
     has
    0.88
     came
    0.87
     went
    0.87
     was
    0.82
     have
    0.82
    RegistryLite
    0.81
    Activations Density 0.224%

    No Known Activations