Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 13779
    Prev
    Next
    INDEX
    Explanations

    expressions of enjoyment and pleasure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     devenus
    -0.59
    ñata
    -0.56
     Maintenant
    -0.55
     troppo
    -0.55
     godfather
    -0.54
     élevées
    -0.54
     avions
    -0.54
     Gibbons
    -0.54
    FormState
    -0.54
     onCancelled
    -0.54
    POSITIVE LOGITS
     pleasure
    1.78
     enjoy
    1.52
     delight
    1.44
    pleasure
    1.43
     Pleasure
    1.41
     joy
    1.35
     Enjoy
    1.34
     enjoyment
    1.31
    Enjoy
    1.30
    joy
    1.24
    Activations Density 0.046%

    No Known Activations