© 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. 18-GEMMASCOPE-RES-16K
    11. 4219
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and enjoyment in collaborative work experiences

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

    Expressing enjoyment or pleasure

    np_acts-logits-general · gemini-2.0-flash

    enjoyment of experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.66
     समीक्षक
    -0.64
    ご注意
    -0.62
    mybatisplus
    -0.61
    Numerology
    -0.58
    CodeAttribute
    -0.57
    itinéraire
    -0.57
     الدولى
    -0.55
     հղումներ
    -0.55
    GEBURTS
    -0.54
    POSITIVE LOGITS
     watching
    1.16
     seeing
    1.05
     hearing
    1.00
     Watching
    0.97
    watching
    0.91
    Watching
    0.91
     interacting
    0.81
     watch
    0.77
    hearing
    0.75
     Seeing
    0.75
    Activations Density 0.263%

    No Known Activations