© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 12622
    Prev
    Next
    INDEX
    Explanations

    elements related to visual styling in graphical user interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Clik
    -0.60
    hmer
    -0.48
    transQ
    -0.48
    Captor
    -0.47
    IRQn
    -0.46
    cutta
    -0.44
    zeć
    -0.44
    voerd
    -0.44
    opress
    -0.42
    ⎦
    -0.42
    POSITIVE LOGITS
     TextStyle
    2.58
     BoxDecoration
    1.39
     InputDecoration
    1.19
     BorderSide
    1.09
    TextStyle
    0.96
    textStyle
    0.74
    BoxShadow
    0.72
    styleType
    0.71
    TextSpan
    0.66
     TextAppearance
    0.62
    Activations Density 0.000%

    No Known Activations