© 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. 8570
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly in the context of data or statistical analyses

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

    Chemical composition percentages

    np_acts-logits-general · gemini-2.0-flash

    legal citations and chemical formulas

    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
    :✨
    -0.66
     تكبرها
    -0.59
     وتسجيلات
    -0.54
    rawDesc
    -0.51
    pédie
    -0.51
     RSSSF
    -0.51
     nifer
    -0.49
     naturels
    -0.48
     distanciation
    -0.47
    gués
    -0.47
    POSITIVE LOGITS
    
    0.55
    ImageContext
    0.53
    AndEndTag
    0.49
     facing
    0.49
    Спољашње
    0.49
    enschein
    0.47
    sue
    0.47
    makeConstraints
    0.46
    complexType
    0.46
     hinweg
    0.46
    Activations Density 1.203%

    No Known Activations