© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3269
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and functions

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

    mathematical expressions and LaTeX commands within equations and formulas.

    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
    -0.75
    Autoritní
    -0.70
    DockStyle
    -0.67
    AnimationsModule
    -0.66
    AccessorTable
    -0.66
    Personensuche
    -0.66
     مرئيه
    -0.66
     متعلقه
    -0.65
     otomatig
    -0.64
     AssemblyProduct
    -0.63
    POSITIVE LOGITS
     чем
    0.30
    まだ
    0.29
    box
    0.28
     (
    0.28
     placas
    0.27
     encuentre
    0.27
    框
    0.26
    already
    0.26
    canvas
    0.26
    two
    0.26
    Activations Density 1.043%

    No Known Activations