© 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. 1328
    Prev
    Next
    INDEX
    Explanations

    references to prestigious awards, particularly the Nobel Prize

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

    Awards, prizes, and recognition

    np_acts-logits-general · gemini-2.0-flash

    award and prize names

    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
    aarrggbb
    -0.80
    Personensuche
    -0.70
     Disqus
    -0.64
    UnknownFieldSet
    -0.62
     tartalomajánló
    -0.62
    kuuta
    -0.62
    تقاوى
    -0.60
     '\\;'
    -0.60
    ">//
    -0.60
    IsPostBack
    -0.60
    POSITIVE LOGITS
     award
    2.79
     Award
    2.55
     awards
    2.52
    Award
    2.30
     AWARD
    2.26
    award
    2.26
     Awards
    2.23
     awarded
    2.20
    Awards
    2.08
     winner
    2.03
    Activations Density 0.372%

    No Known Activations