© 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. 10453
    Prev
    Next
    INDEX
    Explanations

    references to the word "fa," indicating a focus on common or notable uses of the term

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

    Token "Fa" or "fa" at the beginning of words

    np_acts-logits-general · gemini-2.0-flash

    words starting with Fa

    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
    Datuak
    -0.73
    Ārējās
    -0.73
    Демографія
    -0.73
    PerformLayout
    -0.70
    ResumeLayout
    -0.69
    Източници
    -0.67
     BorderLayout
    -0.66
    ISupport
    -0.66
    ագրություններ
    -0.65
     Púb
    -0.64
    POSITIVE LOGITS
     fa
    0.84
     Fa
    0.73
    Fa
    0.62
    fa
    0.59
    Faz
    0.53
     Faz
    0.53
     fanno
    0.50
     phased
    0.49
     Фа
    0.49
    hlon
    0.47
    Activations Density 0.113%

    No Known Activations