© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13539
    Prev
    Next
    INDEX
    Explanations

    instances of the word "understand" or its variations

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

    "understand" or "understanding"

    np_acts-logits-general · gemini-2.0-flash

    concept of understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    latLng
    -0.42
    ambién
    -0.40
     Dishes
    -0.40
    ListPage
    -0.39
     rpc
    -0.39
     dishes
    -0.39
     liệt
    -0.38
     dish
    -0.37
     auroit
    -0.36
     Bounty
    -0.35
    POSITIVE LOGITS
     Understanding
    1.27
     understanding
    1.25
    Understanding
    1.23
     understand
    1.21
     Understand
    1.20
    understanding
    1.19
    understand
    1.17
     understands
    1.16
    Understand
    1.13
     understood
    0.99
    Activations Density 0.120%

    No Known Activations