© 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. 28-GEMMASCOPE-RES-16K
    11. 7840
    Prev
    Next
    INDEX
    Explanations

    references to types of neurons and neural networks

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

    "Ne" followed by lowercase letters

    np_acts-logits-general · gemini-2.0-flash

    Ne words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.84
    出版年
    -0.76
    ViewFeatures
    -0.74
     kasarigan
    -0.69
     &___
    -0.68
    mybatisplus
    -0.68
     okuyayım
    -0.68
     للاسماء
    -0.67
    ⤹
    -0.65
     ویکی‌پدی
    -0.64
    POSITIVE LOGITS
     Ne
    0.63
    Ne
    0.55
     NE
    0.48
     ne
    0.47
     Neumann
    0.47
     Neb
    0.42
     Nem
    0.41
    NE
    0.41
     Né
    0.41
     Не
    0.40
    Activations Density 0.218%

    No Known Activations