© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 47277
    Prev
    Next
    INDEX
    Explanations

    references to the Star Wars universe

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

    Star Wars franchise

    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
     Micha
    -0.35
     Hickey
    -0.35
     Upton
    -0.34
     Sampson
    -0.34
     dedicated
    -0.34
    รม
    -0.34
    konzept
    -0.33
     suceso
    -0.33
     Olsson
    -0.33
     Kepala
    -0.33
    POSITIVE LOGITS
    patine
    0.82
     Skywalker
    0.80
     ***!
    0.69
     lightsaber
    0.68
     Kenobi
    0.67
     Jedi
    0.64
     Yoda
    0.62
     Galactic
    0.62
    
    0.61
     galactic
    0.61
    Activations Density 0.017%

    No Known Activations