© 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. 80306
    Prev
    Next
    INDEX
    Explanations

    instances of the word "dict" and its variations in the text

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

    dictator

    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
    település
    -0.65
    odeon
    -0.59
    ization
    -0.58
     Kearney
    -0.57
     Waterman
    -0.56
     Horowitz
    -0.56
    oser
    -0.55
    extension
    -0.55
     ura
    -0.55
    //
    -0.54
    POSITIVE LOGITS
    dict
    0.67
     dict
    0.60
    Dict
    0.60
     Dict
    0.59
    Vict
    0.50
    ict
    0.48
     appelez
    0.47
     createState
    0.47
     Dept
    0.45
     Vict
    0.45
    Activations Density 0.007%

    No Known Activations