© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 8973
    Prev
    Next
    INDEX
    Explanations

    instances of the word "full" and variations of it, especially in reference to attributes or measurements

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

    "Full" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    phrases starting with "full"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     altogether
    -0.74
    +#+
    -0.66
    EDEFAULT
    -0.65
     vivement
    -0.56
     célèbres
    -0.55
     entirely
    -0.54
    zdo
    -0.52
     meille
    -0.52
     terlaris
    -0.52
     wholly
    -0.52
    POSITIVE LOGITS
     blown
    1.12
    blown
    1.01
    fledged
    0.96
     fled
    0.94
    fillment
    0.80
     throttle
    0.79
    erton
    0.76
     spectrum
    0.76
     full
    0.75
     disclosure
    0.74
    Activations Density 0.110%

    No Known Activations