© 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. 83531
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "year" and its variations in different contexts

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

    year-related time periods

    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
     McKenzie
    -0.52
     McLeod
    -0.51
     McN
    -0.47
    envolvimento
    -0.46
     McIntosh
    -0.45
     McL
    -0.45
     abzu
    -0.45
     çı
    -0.45
     Madsen
    -0.44
     Gib
    -0.43
    POSITIVE LOGITS
    Year
    1.40
     Year
    1.35
     year
    1.28
     YEAR
    1.27
    YEAR
    1.22
    year
    1.16
     año
    1.02
    getYear
    1.02
     année
    1.00
     years
    0.97
    Activations Density 0.061%

    No Known Activations