© 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. 22-GEMMASCOPE-RES-16K
    11. 14378
    Prev
    Next
    INDEX
    Explanations

    phrases associated with coexistence and social responsibility

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

    Adverbs ending in "-ly"

    np_acts-logits-general · gemini-2.0-flash

    adverbs describing manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quelcon
    -0.96
     récents
    -0.87
     sociala
    -0.85
     supérieures
    -0.83
     vectorielles
    -0.82
     greateſt
    -0.82
     automatiques
    -0.81
     łat
    -0.80
     tantum
    -0.79
     rapides
    -0.79
    POSITIVE LOGITS
     creatively
    0.92
     thoughtfully
    0.87
     sensibly
    0.87
     intelligently
    0.85
     wisely
    0.85
     smartly
    0.84
     efficiently
    0.82
     meaningfully
    0.80
     aggressively
    0.79
     responsibly
    0.78
    Activations Density 1.298%

    No Known Activations