© 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 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. 7070
    Prev
    Next
    INDEX
    Explanations

    icons associated with interactive user interface elements

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

    Font Awesome icon class names and references.

    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
     autorytatywna
    -0.60
    出版年
    -0.57
    存于互联网档案馆
    -0.57
    MethodManager
    -0.57
    Referències
    -0.56
    setVerticalGroup
    -0.54
    queryInterface
    -0.53
     ویکی‌پدیای
    -0.52
    delwed
    -0.51
     CreateTagHelper
    -0.51
    POSITIVE LOGITS
     fa
    0.53
     Fa
    0.45
    fw
    0.41
    fa
    0.41
     code
    0.39
     vVar
    0.39
     card
    0.39
     Recovery
    0.38
     Liv
    0.37
     Shoemaker
    0.36
    Activations Density 0.024%

    No Known Activations