© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 94468
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "different."

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

    different distinctions

    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
    charCode
    -0.54
    inghouse
    -0.50
    scrollView
    -0.47
    capai
    -0.47
     heißen
    -0.46
    IconModule
    -0.45
    kemeja
    -0.45
    べく
    -0.45
    ola
    -0.45
     âmes
    -0.44
    POSITIVE LOGITS
    Different
    0.90
     Different
    0.88
     DIFFERENT
    0.87
    different
    0.86
     different
    0.84
     farklı
    0.66
    erent
    0.64
     différent
    0.63
     diferente
    0.63
     distinta
    0.63
    Activations Density 0.038%

    No Known Activations