© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 31611
    Prev
    Next
    INDEX
    Explanations

    traits and qualities related to perception and humor

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

    keen sense or flair

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     strerror
    -0.40
    Externé
    -0.39
    lankton
    -0.39
     betweenstory
    -0.39
    ruvate
    -0.38
     nadzieję
    -0.38
    وفاته
    -0.37
    秽
    -0.37
     Wikispecies
    -0.37
     lenker
    -0.37
    POSITIVE LOGITS
     discerning
    0.65
     discernment
    0.65
     astute
    0.63
     foresight
    0.58
     acumen
    0.57
     keen
    0.54
    眼光
    0.53
     perceptive
    0.52
     &___
    0.51
     shrewd
    0.50
    Activations Density 0.014%

    No Known Activations