© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 14807
    Prev
    Next
    INDEX
    Explanations

    phrases related to protective gear and health safety measures

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

    "mask" or "masks"

    np_acts-logits-general · gemini-2.0-flash

    masks

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     <>",
    -0.83
     <<<<<<<<<<<<<<
    -0.62
    VersionUID
    -0.61
    TagMode
    -0.58
     متعلقه
    -0.58
     незавершена
    -0.58
    LabelTagHelper
    -0.55
    ContentAsync
    -0.54
    IVEREF
    -0.51
    omitempty
    -0.51
    POSITIVE LOGITS
     masks
    1.91
     mask
    1.86
     Masks
    1.59
    Mask
    1.57
     Mask
    1.57
    mask
    1.52
    Masks
    1.50
     masking
    1.45
     MASK
    1.44
    masks
    1.41
    Activations Density 0.156%

    No Known Activations