© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 106143
    Prev
    Next
    INDEX
    Explanations

    mathematical definitions and properties related to systems and matrices

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

    Mathematical notation and connecting phrases in academic mathematics text, particularly elements that structure formal definitions, axioms, and properties.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     concre
    -0.41
    solu
    -0.40
    addLast
    -0.39
    phosa
    -0.39
    deos
    -0.38
    lamic
    -0.37
    FFER
    -0.37
    emlrt
    -0.37
    sensor
    -0.36
    Edu
    -0.36
    POSITIVE LOGITS
    Autoritní
    0.52
    AndroidJUnit
    0.50
     XCTest
    0.49
     autorytatywna
    0.47
    ApplicationTests
    0.45
    VYMaps
    0.45
    évaluateur
    0.43
     Roskov
    0.43
     Italijanski
    0.42
    UnitTesting
    0.42
    Activations Density 0.367%

    No Known Activations