© 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. 21-GEMMASCOPE-RES-16K
    11. 14463
    Prev
    Next
    INDEX
    Explanations

    specific terms related to scientific measurements and experimental processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.99
    LookAnd
    -0.90
     disambiguazione
    -0.87
    TagMode
    -0.82
    RenderAtEndOf
    -0.79
     للاسماء
    -0.78
     चीज़ों
    -0.76
    IContainer
    -0.75
     समीक्षाओं
    -0.71
    Vidite
    -0.71
    POSITIVE LOGITS
     deſt
    0.78
     juſ
    0.78
     uſed
    0.76
     myſelf
    0.76
     abſ
    0.75
     ſta
    0.75
     Inſ
    0.75
     againſt
    0.73
     ſever
    0.72
     noft
    0.72
    Activations Density 1.748%

    No Known Activations