© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 14022
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Fa" and related variations or derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     længere
    -0.43
     hodin
    -0.39
    writeField
    -0.39
     hodiny
    -0.38
     naming
    -0.36
    println
    -0.36
    ніципалі
    -0.36
    ſh
    -0.35
     Verhältnisse
    -0.35
    writeObject
    -0.35
    POSITIVE LOGITS
    fortawesome
    0.71
     fa
    0.62
    FAD
    0.57
     Fä
    0.49
     Фа
    0.49
     Fa
    0.49
    fad
    0.48
    Fa
    0.48
    fa
    0.48
     FA
    0.47
    Activations Density 0.255%

    No Known Activations