© 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. 3854
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or institutions named "Smith."

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

    "Smith" followed by various suffixes

    np_acts-logits-general · gemini-2.0-flash

    the name Smith

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Anſ
    -0.83
     whoſe
    -0.78
     Conſ
    -0.78
     unſ
    -0.76
     ſind
    -0.76
     Eſ
    -0.75
     Houſe
    -0.73
     Diſ
    -0.73
     Reſ
    -0.73
     ſec
    -0.70
    POSITIVE LOGITS
     فريبيس
    0.82
     AspNetCore
    0.82
     initComponents
    0.69
     oprot
    0.67
    awtextra
    0.65
     HasFactory
    0.64
    NSON
    0.63
     <=",
    0.61
    
    0.60
     متعلقه
    0.59
    Activations Density 0.237%

    No Known Activations