© 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. 14-GEMMASCOPE-RES-16K
    11. 9260
    Prev
    Next
    INDEX
    Explanations

    numerical values and their associations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    delwed
    -0.36
    ToTensor
    -0.33
     consideramos
    -0.33
     cord
    -0.29
    rawtypes
    -0.29
     front
    -0.28
     rad
    -0.28
     ger
    -0.27
     revolution
    -0.27
     carbon
    -0.27
    POSITIVE LOGITS
    StructEnd
    0.73
     للاسماء
    0.68
    Tembelea
    0.66
     ویکی‌پدیا
    0.65
     kasarigan
    0.64
    期刊论文
    0.62
    JspWriter
    0.62
     PeEnEo
    0.61
     ComVisible
    0.61
     فريبيس
    0.60
    Activations Density 0.588%

    No Known Activations