© 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. 1677
    Prev
    Next
    INDEX
    Explanations

    elements related to discussions about decisions and opinions

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

    sentences expressing personal beliefs and reflections on parenting and education

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

    if I/we would

    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
     autorytatywna
    -0.78
    webElementXpaths
    -0.76
    "]="
    -0.74
    EXPECT
    -0.73
    ModelSerializer
    -0.72
    ésultat
    -0.71
    зулта
    -0.71
    SourceChecksum
    -0.70
    parsedMessage
    -0.69
     étoit
    -0.69
    POSITIVE LOGITS
     would
    3.30
    would
    2.85
     Would
    2.68
    Would
    2.58
     WOULD
    2.37
     wouldn
    2.03
    wouldn
    1.72
     lenne
    1.72
     could
    1.69
     Wouldn
    1.69
    Activations Density 1.587%

    No Known Activations