© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 908
    Prev
    Next
    INDEX
    Explanations

    names of people and products along with their related details

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

    Uncommon terms (possibly non-English)

    np_acts-logits-general · gemini-2.0-flash

    nationality, medical conditions, counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    B
    -0.28
    in
    -0.27
     l
    -0.25
    soever
    -0.24
     j
    -0.24
    is
    -0.24
    l
    -0.24
    j
    -0.24
    d
    -0.24
     fellow
    -0.24
    POSITIVE LOGITS
    XmlAccessType
    0.85
     مرئيه
    0.80
    MessageOf
    0.75
     Paglinawan
    0.75
     ویکی‌پدی
    0.75
     pinulongan
    0.73
     kasarigan
    0.72
     дописавши
    0.72
     للمعارف
    0.71
    Tembelea
    0.70
    Activations Density 1.004%

    No Known Activations