© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16-GEMMASCOPE-RES-16K
    11. 5854
    Prev
    Next
    INDEX
    Explanations

    terms related to fluorescence and flow measurement techniques

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

    containing "flor" or "flu"

    np_acts-logits-general · gemini-2.0-flash

    Flor, Flu, Flow words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subtra
    -0.78
    makeConstraints
    -0.74
     QV
    -0.74
     Atkinson
    -0.74
     PPD
    -0.74
     Königreich
    -0.72
     Reiche
    -0.72
    DispatchToProps
    -0.72
    nthesis
    -0.70
    *@
    -0.70
    POSITIVE LOGITS
     FL
    1.06
     Fl
    1.05
     FLOR
    1.05
    fl
    1.03
    flu
    1.01
     FLO
    1.00
     Flur
    1.00
    FLU
    1.00
     Фло
    1.00
    flow
    0.99
    Activations Density 0.118%

    No Known Activations