© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 10182
    Prev
    Next
    INDEX
    Explanations

    instances of the word "enjoy" and its variations, indicating a focus on enjoyment or positive experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.78
    JspWriter
    -0.69
    FailureListener
    -0.62
    ეტ
    -0.58
     Krakowie
    -0.57
     chng
    -0.57
    urlpatterns
    -0.54
    oa̍t
    -0.54
     sayap
    -0.53
    unknownFields
    -0.52
    POSITIVE LOGITS
     Enjoy
    0.77
     enjoyment
    0.69
    endence
    0.69
     enjoying
    0.68
     disfru
    0.68
    Enjoy
    0.67
     enjoyed
    0.66
     enjoy
    0.66
    console
    0.65
    Enjoying
    0.65
    Activations Density 0.037%

    No Known Activations