© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14007
    Prev
    Next
    INDEX
    Explanations

    expressions of joy and fulfillment related to teaching and learning experiences

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

    Positive experiences or feelings

    np_acts-logits-general · gemini-2.0-flash

    feeling of joy and gratitude

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    CopyWith
    -0.68
    expandindo
    -0.59
    DrawerToggle
    -0.55
    Handlung
    -0.54
    IsMutable
    -0.52
    Chham
    -0.52
    ActionCreators
    -0.52
    parsedMessage
    -0.51
    yntaxException
    -0.50
     հղումներ
    -0.50
    POSITIVE LOGITS
     joy
    0.47
     moments
    0.44
     realization
    0.42
     realisation
    0.41
     moment
    0.40
     exhilar
    0.39
     when
    0.38
     feeling
    0.37
     gently
    0.36
     satisfying
    0.36
    Activations Density 0.198%

    No Known Activations