© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8195
    Prev
    Next
    INDEX
    Explanations

    categories and classifications within scientific or technical contexts

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

    Ways of classifying or dividing items

    np_acts-logits-general · gemini-2.0-flash

    classified or divided into types

    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
     Meksiku
    -0.61
     AssemblyTitle
    -0.61
    पया
    -0.59
     useAppContext
    -0.57
    RegressionTest
    -0.57
    isSuccessful
    -0.51
    Palmar
    -0.51
    AccessorTable
    -0.51
     Jove
    -0.50
     kỷ
    -0.50
    POSITIVE LOGITS
     divided
    1.28
    分为
    1.24
     two
    1.18
    divided
    1.13
     Types
    1.11
     types
    1.08
     three
    1.06
    两种
    1.04
     twofold
    1.02
    三种
    1.01
    Activations Density 0.638%

    No Known Activations