© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6815
    Prev
    Next
    INDEX
    Explanations

    mention or references to the term "FI" and its various contexts

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

    Tokens starting with "Fi" or "fi"

    np_acts-logits-general · gemini-2.0-flash

    Fiamce, Fiberglass, Fibula, Fiors, FiH

    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
    +#+#
    -1.07
    StructEnd
    -0.75
     Wikispecies
    -0.70
    dafx
    -0.68
    клопе
    -0.67
    المناصب
    -0.64
     PyLong
    -0.63
     بيها
    -0.63
     للمعارف
    -0.63
    хьтан
    -0.62
    POSITIVE LOGITS
     fi
    0.59
    berglass
    0.54
    Фи
    0.52
    inspiration
    0.52
     фи
    0.50
     Fi
    0.49
    eapple
    0.49
     Fis
    0.49
    endish
    0.49
    odoro
    0.47
    Activations Density 0.148%

    No Known Activations