© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 333
    Prev
    Next
    INDEX
    Explanations

    references to layout and padding specifications in code

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

    XML attributes and their values in Android layout code

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

    . Thus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Padding
    -1.13
    padding
    -1.12
     padding
    -1.07
    Padding
    -1.06
    PADDING
    -1.03
    +#+#
    -0.90
     padded
    -0.90
     Pad
    -0.81
    pad
    -0.78
    padded
    -0.77
    POSITIVE LOGITS
    ftagPool
    0.50
    RectangleBorder
    0.50
     Floors
    0.48
     floor
    0.44
     ста
    0.44
    IFS
    0.43
     للاسماء
    0.43
    格式
    0.43
     OpenAPI
    0.42
     floors
    0.42
    Activations Density 0.006%

    No Known Activations