© 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. 2721
    Prev
    Next
    INDEX
    Explanations

    cute and stylish designs or patterns in products

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

    words related to fabric, design, and aesthetic qualities.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    SourceChecksum
    -0.66
    Jereo
    -0.60
     المعيارى
    -0.59
     Chwiliwch
    -0.54
    endpush
    -0.54
    ChildScrollView
    -0.54
    AddTagHelper
    -0.52
     vectorielle
    -0.51
    verifyException
    -0.50
    complexContent
    -0.50
    POSITIVE LOGITS
     stylish
    0.65
     defaultstate
    0.57
     sleek
    0.57
     design
    0.56
     aesthetics
    0.53
     elegant
    0.52
     aesthetic
    0.51
     style
    0.50
     chic
    0.50
     classy
    0.47
    Activations Density 0.112%

    No Known Activations