© 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. 15772
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts related to morphisms and isomorphisms

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

    before/after "is" in mathematical contexts

    np_acts-logits-general · gemini-2.0-flash

    is homomorphism or projection

    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
     للمعارف
    -0.88
     تضيفلها
    -0.70
    +#+
    -0.70
     ErrIntOverflow
    -0.66
     WaitForSeconds
    -0.65
    AutoresizingMask
    -0.65
    CloseOperation
    -0.64
     שוליים
    -0.63
    afficheront
    -0.63
    __':
    -0.61
    POSITIVE LOGITS
     map
    1.16
     Map
    1.04
     mapping
    1.02
     maps
    0.99
    Map
    0.99
    map
    0.98
     Maps
    0.92
    Maps
    0.90
    mapping
    0.89
    映射
    0.85
    Activations Density 1.533%

    No Known Activations