© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 9811
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms related to organizations, specifically in the context of health and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.75
     تضيفلها
    -0.67
    bootstrapcdn
    -0.64
    原始内容存档于
    -0.61
    رشف
    -0.60
    liothèque
    -0.54
    trane
    -0.53
    Hozzáférés
    -0.52
    шення
    -0.51
    allible
    -0.51
    POSITIVE LOGITS
     betweenstory
    0.74
     CWE
    0.72
     ſta
    0.64
     seyn
    0.62
     genotyping
    0.61
     $_
    0.60
     ſaid
    0.60
     viſ
    0.58
    gwt
    0.58
     MC
    0.57
    Activations Density 0.673%

    No Known Activations