© 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. 1788
    Prev
    Next
    INDEX
    Explanations

    elements related to computer programming and configuration

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

    Followed by verbs in other languages

    np_acts-logits-general · gemini-2.0-flash

    forms of "to be" and "can"

    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
     StatefulWidget
    -0.71
    Geplaatst
    -0.69
    WithIOException
    -0.69
    المكان
    -0.69
    !*\
    -0.64
     AssemblyCulture
    -0.64
    ///</
    -0.62
    tometer
    -0.61
    woofer
    -0.61
    RenderAtEndOf
    -0.61
    POSITIVE LOGITS
     be
    2.15
    be
    1.31
     soient
    1.23
     Be
    1.20
    Be
    1.12
     possa
    1.11
     legyen
    1.08
     puisse
    1.05
     puissent
    1.03
     abbia
    1.01
    Activations Density 0.304%

    No Known Activations