© 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. 11596
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or proper nouns

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

    after first names or articles

    np_acts-logits-general · gemini-2.0-flash

    the Bushes

    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
     préc
    -0.64
     Theſe
    -0.62
     lèvres
    -0.59
     nationaux
    -0.59
     récentes
    -0.59
     marquées
    -0.56
     concernés
    -0.56
     للاسماء
    -0.56
     AssemblyTitle
    -0.55
     barnen
    -0.55
    POSITIVE LOGITS
     Indias
    0.97
    kespea
    0.94
     Smiths
    0.92
    cys
    0.84
    Americas
    0.83
     didnt
    0.82
     childs
    0.82
     wasnt
    0.79
    Whats
    0.79
     couldnt
    0.79
    Activations Density 0.205%

    No Known Activations