© 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. 905
    Prev
    Next
    INDEX
    Explanations

    terms related to health conditions and effects

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

    Follows certain punctuation or formatting

    np_acts-logits-general · gemini-2.0-flash

    heart jump

    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
     Verfü
    -0.57
    #+#
    -0.56
     MOND
    -0.53
     متعلقه
    -0.52
     caractéris
    -0.52
    Gesture
    -0.51
    ifflin
    -0.51
     Grinding
    -0.50
    ModelSerializer
    -0.49
    ATIVO
    -0.49
    POSITIVE LOGITS
    Tikang
    0.69
     ModelExpression
    0.67
     instantly
    0.63
    )))));
    0.60
    GeoNames
    0.56
    🇶
    0.55
     finally
    0.55
     jsPsych
    0.54
     indeed
    0.54
     faintly
    0.52
    Activations Density 0.056%

    No Known Activations