Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 8318
    Prev
    Next
    INDEX
    Explanations

    references to Jedi and associated training elements from the Star Wars universe

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.71
     Roumanie
    -0.59
     nucléaire
    -0.57
     Birmingham
    -0.56
    wahati
    -0.56
     Walling
    -0.55
     Kupfer
    -0.55
    InstrumentedTest
    -0.54
     vanadium
    -0.51
     stanovnika
    -0.51
    POSITIVE LOGITS
     Jedi
    1.18
     Anakin
    1.16
     Yoda
    1.10
     Skywalker
    1.09
     Vader
    1.06
     Obi
    1.06
     Darth
    1.03
     Kenobi
    1.00
    Jedi
    0.99
     lightsaber
    0.98
    Activations Density 0.179%

    No Known Activations