© 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. 5757
    Prev
    Next
    INDEX
    Explanations

    expressions related to comprehension and understanding

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

    "Understand" and related words

    np_acts-logits-general · gemini-2.0-flash

    understanding

    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
    datagrid
    -0.59
    jupiter
    -0.59
    glBindTexture
    -0.58
    userManager
    -0.54
    an
    -0.50
    orianCalendar
    -0.49
    isholm
    -0.48
    Notable
    -0.47
    لاثة
    -0.46
     perdana
    -0.45
    POSITIVE LOGITS
     why
    1.00
     Understand
    0.93
    understand
    0.91
    Understand
    0.88
     comprehend
    0.85
     understands
    0.84
    ably
    0.81
     begrij
    0.81
     understand
    0.78
     entiende
    0.77
    Activations Density 0.073%

    No Known Activations