© 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. 3342
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or emotional reaction

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

    Japanese words starting with "a"

    np_acts-logits-general · gemini-2.0-flash

    アズミ様 and アズサ様

    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
     descar
    -0.43
    ierr
    -0.42
    ưỡi
    -0.42
    RUNTIME
    -0.42
     coming
    -0.41
    __(/*!
    -0.41
    成
    -0.40
     Rois
    -0.40
     pay
    -0.39
     Vard
    -0.38
    POSITIVE LOGITS
     ResourceManager
    0.67
    extAlignment
    0.65
    wahati
    0.62
     uſed
    0.61
     gawas
    0.59
     Majefty
    0.58
    localctx
    0.57
     bruto
    0.57
     leaſt
    0.57
    noinspection
    0.57
    Activations Density 0.086%

    No Known Activations