© 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. 76331
    Prev
    Next
    INDEX
    Explanations

    references to specific names, particularly "Lorenzo" and variations of the name "Lager."

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

    Lorenzo, DiLorenzo, Lager, Jäger

    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
    httphttps
    -0.63
    windowFixed
    -0.59
     otomatig
    -0.59
    FormTagHelper
    -0.59
    Vinci
    -0.56
     autorytatywna
    -0.56
     Vainqueur
    -0.55
     Vinci
    -0.55
    Wilson
    -0.54
     hemo
    -0.54
    POSITIVE LOGITS
     Lager
    2.03
     lager
    1.78
    Lager
    1.73
    lager
    1.23
     лагер
    0.68
    AGER
    0.54
     laag
    0.52
     maga
    0.52
    ager
    0.51
     Larger
    0.50
    Activations Density 0.002%

    No Known Activations