© 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. 11-GEMMASCOPE-RES-16K
    6. 4642
    Prev
    Next
    INDEX
    Explanations

    positive traits and themes associated with humor and wisdom

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreExecute
    -0.72
    endpush
    -0.70
    Personensuche
    -0.65
    adaptiveStyles
    -0.61
     esso
    -0.60
     mág
    -0.59
     vierge
    -0.59
    SOUNDBITE
    -0.58
     honte
    -0.58
     acrylique
    -0.57
    POSITIVE LOGITS
     irrever
    0.57
     nonchal
    0.54
    textTheme
    0.54
     subtle
    0.52
     giản
    0.51
     style
    0.50
     wit
    0.50
    wit
    0.49
     Gains
    0.48
     STYLE
    0.48
    Activations Density 0.182%

    No Known Activations