© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 126089
    Prev
    Next
    INDEX
    Explanations

    references to programming elements and mathematical expressions

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

    special characters, Greek letters, and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    lesias
    -0.38
    حياته
    -0.37
     îns
    -0.36
     Schulter
    -0.34
     článek
    -0.34
     beliau
    -0.32
     Corazón
    -0.32
    AndEndTag
    -0.32
     Suiza
    -0.32
     hombros
    -0.31
    POSITIVE LOGITS
    migrationBuilder
    0.64
    NgModule
    0.58
     transfieras
    0.53
     kaynağından
    0.51
     autorytatywna
    0.51
    orice
    0.50
    észetes
    0.50
     esternos
    0.49
    featureID
    0.49
     utafitiHapana
    0.49
    Activations Density 0.081%

    No Known Activations