© 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. 20-GEMMASCOPE-RES-16K
    11. 8613
    Prev
    Next
    INDEX
    Explanations

    references to "Fe" as it relates to scientific and technical contexts

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

    The token "fe"

    np_acts-logits-general · gemini-2.0-flash

    fe or Fe

    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
     виправивши
    -0.77
    شهاد
    -0.69
    __.__
    -0.67
    SBATCH
    -0.65
    RenderAtEndOf
    -0.64
    ksikon
    -0.62
    verwijspagina
    -0.58
    Repost
    -0.57
    ToScroll
    -0.57
    versaire
    -0.57
    POSITIVE LOGITS
     Fe
    0.85
    Fe
    0.84
     fe
    0.79
     FE
    0.72
    FE
    0.65
    fees
    0.62
    fe
    0.59
     Fel
    0.59
     Fee
    0.56
     fees
    0.56
    Activations Density 0.105%

    No Known Activations