© 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. 31-GEMMASCOPE-RES-16K
    11. 65
    Prev
    Next
    INDEX
    Explanations

    special characters and quotes indicating dialogue or quotations in text

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

    words enclosed in quotation marks that represent abstract concepts or qualities.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    原始内容存档于
    -0.29
    「
    -0.27
     berupa
    -0.26
    、「
    -0.23
     وتسجيلات
    -0.23
     arşivlendi
    -0.23
    『
    -0.23
    存于互联网档案馆
    -0.22
    ‪
    -0.20
     către
    -0.20
    POSITIVE LOGITS
    :✨
    0.92
    niſſe
    0.90
    BibitemShut
    0.89
    WithIOException
    0.88
    mpagne
    0.87
    Tikang
    0.85
     <>",
    0.85
     queſto
    0.84
    iſchen
    0.84
    iſche
    0.84
    Activations Density 0.289%

    No Known Activations