© 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. 9-GEMMASCOPE-RES-131K
    11. 39330
    Prev
    Next
    INDEX
    Explanations

    instances of the word "repeat" in various contexts

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

    repeat, repeats, repeating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     currentNode
    -0.50
     newUser
    -0.50
     Nvidia
    -0.48
    artements
    -0.48
     NSCoder
    -0.47
     polisi
    -0.46
    sApp
    -0.46
     handleClick
    -0.45
     blumen
    -0.45
     userName
    -0.45
    POSITIVE LOGITS
     repeat
    2.50
    repeat
    2.47
    Repeat
    2.33
     Repeat
    2.33
     repeats
    1.98
    REPEAT
    1.87
    repe
    1.58
     repeating
    1.56
     Repe
    1.54
     repetir
    1.48
    Activations Density 0.012%

    No Known Activations