© 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. 14943
    Prev
    Next
    INDEX
    Explanations

    specific terminology related to biological species and genetic analysis

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

    Tokens after "the"

    np_acts-logits-general · gemini-2.0-flash

    caribbean islands

    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
     Monza
    -0.61
     Shasta
    -0.58
     CreateTagHelper
    -0.56
     Spokane
    -0.53
     Sequo
    -0.50
     Coulter
    -0.49
     Himo
    -0.48
    nsan
    -0.47
     ihop
    -0.47
    beutel
    -0.47
    POSITIVE LOGITS
     Caribbean
    1.20
    Caribbean
    1.04
     Barbados
    0.99
     Bahamas
    0.95
     Antigua
    0.93
     Nevis
    0.92
     caribbean
    0.88
     Dominica
    0.87
     Cari
    0.85
    Barbados
    0.85
    Activations Density 0.114%

    No Known Activations