© 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. 15-GEMMASCOPE-RES-16K
    11. 6289
    Prev
    Next
    INDEX
    Explanations

    text related to ceramics and tiles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.76
     GenerationType
    -0.75
    IActionResult
    -0.72
    ModelAttribute
    -0.72
    Viited
    -0.70
     Schick
    -0.70
     Thurston
    -0.69
    ruptedException
    -0.68
    webElementXpaths
    -0.67
    جوايز
    -0.67
    POSITIVE LOGITS
     tiles
    1.11
     Tiles
    1.02
     tile
    1.01
     Tile
    0.99
    tiles
    0.94
    tile
    0.92
    Tiles
    0.91
    TILE
    0.90
     Brick
    0.88
    Tile
    0.87
    Activations Density 0.371%

    No Known Activations