© 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. 1893
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical values or mathematical symbols

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

    academic and scientific document formatting, including citations, tables, mathematical notation, and reference markers.

    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
     ब्रेकडाउन
    -0.90
     تضيفلها
    -0.77
     nahilalakip
    -0.76
     '\\;'
    -0.76
    تقاوى
    -0.73
     pinulongan
    -0.70
     AssemblyCulture
    -0.70
     AssemblyCompany
    -0.68
    səhifə
    -0.68
    цездатний
    -0.68
    POSITIVE LOGITS
     FontWeight
    0.42
    mml
    0.40
    [toxicity=0]
    0.36
    enumerate
    0.31
    ‍
    0.29
     nhiên
    0.29
    GroupLayout
    0.29
    — 
    0.29
    0.29
    2
    0.29
    Activations Density 1.020%

    No Known Activations