© 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. 20-GEMMASCOPE-RES-16K
    11. 545
    Prev
    Next
    INDEX
    Explanations

    expressions related to advice or recommendations

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

    French conditional conjunctions

    np_acts-logits-general · gemini-2.0-flash

    si... alors... que... mais

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Gemma-2-2B-L20-Narrative-Cluster
    Social Natural Language (french conjunctions)

    No Comments

    Negative Logits
     lenker
    -0.91
     فريبيس
    -0.90
     AssemblyCompany
    -0.87
     للمعارف
    -0.84
    
    -0.76
    tvguidetime
    -0.74
     مشين
    -0.72
    fromnode
    -0.71
    Билгалдахарш
    -0.70
    Portale
    -0.69
    POSITIVE LOGITS
     it
    0.63
     man
    0.54
     we
    0.52
     Man
    0.45
    it
    0.45
     on
    0.43
    ils
    0.43
     no
    0.43
    findpost
    0.42
    matplotlib
    0.42
    Activations Density 0.085%

    No Known Activations