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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 61065
    Prev
    Next
    INDEX
    Explanations

    references to locations or places, particularly with the suffix 'ville'

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

    place names ending in ville

    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
     CURIAM
    -0.54
     Lancet
    -0.52
    pseud
    -0.52
     informée
    -0.51
    aronder
    -0.51
     Simón
    -0.50
    ToProps
    -0.50
    AfterEach
    -0.49
    saf
    -0.48
    shadow
    -0.47
    POSITIVE LOGITS
    ville
    2.84
    VILLE
    2.50
    villes
    1.87
    Ville
    1.73
     ville
    1.50
     Ville
    1.41
    vile
    1.34
    vill
    1.30
    ILLE
    1.22
    erville
    1.18
    Activations Density 0.004%

    No Known Activations