© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 61934
    Prev
    Next
    INDEX
    Explanations

    references to the name "Julian" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Julian, Emiliano, guillotine

    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
    Negative Logits
    ambién
    -0.51
     bēr
    -0.51
     školy
    -0.48
     srdce
    -0.47
     înd
    -0.46
     adelante
    -0.44
     étro
    -0.44
     picioare
    -0.43
     commandement
    -0.43
     δύ
    -0.43
    POSITIVE LOGITS
     Julian
    2.45
    Julian
    2.30
     Julián
    1.35
     Julien
    1.02
     Juliana
    0.98
     Giuliano
    0.92
    Juli
    0.83
    Julien
    0.82
     Juli
    0.80
    JUL
    0.80
    Activations Density 0.003%

    No Known Activations