© 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. 8131
    Prev
    Next
    INDEX
    Explanations

    the concept of knowledge, particularly in relation to expertise and understanding in various fields

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

    Follows "knowledge," "understanding," or "about"

    np_acts-logits-general · gemini-2.0-flash

    understanding intricacies or workings

    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
     defaultstate
    -0.69
    IsContent
    -0.57
     resourceCulture
    -0.57
    CrossRef
    -0.57
     nakalista
    -0.56
     تضيفلها
    -0.53
    Aholisi
    -0.51
    dataProvider
    -0.51
    writeField
    -0.49
    tualmente
    -0.49
    POSITIVE LOGITS
     intricacies
    1.06
     workings
    0.97
     how
    0.89
     nuances
    0.89
     terminology
    0.81
     complexities
    0.81
     processes
    0.78
     anatomy
    0.76
     subtleties
    0.75
     fonctionnement
    0.73
    Activations Density 0.317%

    No Known Activations