© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8938
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "La" and its variations in text, indicating a focus on French-language references or entities

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

    Tokens starting with "La" or "El"

    np_acts-logits-general · gemini-2.0-flash

    "La" / "El" before proper nouns

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ágenes
    -0.63
     royaltyfri
    -0.61
    inistro
    -0.60
     Gegenteil
    -0.60
     Sénat
    -0.59
     desmotivaciones
    -0.59
     Grüsse
    -0.58
    guiente
    -0.57
    transQ
    -0.57
     navide
    -0.56
    POSITIVE LOGITS
     La
    1.40
    La
    1.26
     El
    1.24
    El
    1.10
     Le
    0.99
     la
    0.97
     LA
    0.88
    Le
    0.88
     el
    0.79
     le
    0.72
    Activations Density 0.141%

    No Known Activations