© 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. 8062
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and structure in the context of a library or framework

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

    Code-related terms and file paths

    np_acts-logits-general · gemini-2.0-flash

    discussion | information | data

    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
     super
    -0.63
    -
    -0.63
     quality
    -0.55
     d
    -0.51
     h
    -0.49
     de
    -0.49
     b
    -0.48
    agissait
    -0.48
     worth
    -0.47
    useEffect
    -0.47
    POSITIVE LOGITS
     estekak
    1.19
    GEBURTSDATUM
    1.16
     pinulongan
    1.15
     disambiguazione
    1.09
    :✨
    1.01
    Personensuche
    0.99
    Autoritní
    0.97
     transfieras
    0.96
    rungsseite
    0.94
    RectangleBorder
    0.93
    Activations Density 0.388%

    No Known Activations