© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 38309
    Prev
    Next
    INDEX
    Explanations

    terms related to auxiliary functions or structures, particularly in a programming or mathematical context

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

    auxiliary

    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
     Gallimard
    -0.52
    rrrrrrrr
    -0.52
     Irán
    -0.52
    rrrrrr
    -0.50
    sendRedirect
    -0.50
    rrrrr
    -0.50
     Comprometido
    -0.50
     suaminya
    -0.49
    owanego
    -0.49
    rrrr
    -0.48
    POSITIVE LOGITS
     Aux
    1.23
    Aux
    1.11
     aux
    1.05
     AUX
    1.00
    Auxiliary
    0.97
     auxiliary
    0.93
     Auxiliary
    0.93
    aux
    0.88
     auxili
    0.85
    AUX
    0.80
    Activations Density 0.006%

    No Known Activations