© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 11282
    Prev
    Next
    INDEX
    Explanations

    contexts that invoke feelings of enjoyment and fun

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vectorielle
    -0.82
    Награды
    -0.73
     provisoire
    -0.72
    Discografia
    -0.71
     arşivlendi
    -0.71
     noiembrie
    -0.71
     hieronder
    -0.69
     ReactDOM
    -0.69
     littéraire
    -0.68
     Normdatei
    -0.68
    POSITIVE LOGITS
     fun
    3.26
    fun
    2.77
     Fun
    2.75
     FUN
    2.73
    Fun
    2.69
    FUN
    2.46
     divertido
    1.63
     Spaß
    1.61
     diversión
    1.48
     enjoyable
    1.43
    Activations Density 0.044%

    No Known Activations