© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12827
    Prev
    Next
    INDEX
    Explanations

    mentions of arts and related educational activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    новниш
    -0.48
    SequentialGroup
    -0.44
     Comprehension
    -0.42
    Reprints
    -0.39
    adeloupe
    -0.38
     Pública
    -0.38
     Púb
    -0.37
     Steak
    -0.36
    mmä
    -0.36
     капсу
    -0.35
    POSITIVE LOGITS
     artistic
    0.94
     artists
    0.93
     Artists
    0.87
    artists
    0.85
    Artists
    0.85
    Artist
    0.84
     artist
    0.83
     Artist
    0.82
    artist
    0.81
     Artistic
    0.79
    Activations Density 0.218%

    No Known Activations