© 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. 1050
    Prev
    Next
    INDEX
    Explanations

    references to judicial or legal terms and related entities

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

    Follows place names or company names

    np_acts-logits-general · gemini-2.0-flash

    geographic names, technical terms, legal terms, questions

    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
     quæ
    -0.59
     eorum
    -0.52
     épis
    -0.52
     élastique
    -0.51
     času
    -0.50
     blessés
    -0.50
     poffe
    -0.49
     škoda
    -0.49
     caufe
    -0.49
     vacacionales
    -0.48
    POSITIVE LOGITS
    ReusableCell
    1.03
    IntoConstraints
    0.96
     المعيارى
    0.92
     propOrder
    0.92
    TagMode
    0.90
    SequentialGroup
    0.89
    URLException
    0.88
    abestanden
    0.86
     Audiodateien
    0.85
     betweenstory
    0.84
    Activations Density 0.702%

    No Known Activations