© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14993
    Prev
    Next
    INDEX
    Explanations

    references to the term "Le" in various contexts

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

    Following "Le" in French and names

    np_acts-logits-general · gemini-2.0-flash

    Le followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sorte
    -0.54
    **********/
    -0.48
     just
    -0.47
     événement
    -0.47
     Studie
    -0.46
     itinéraire
    -0.44
     exactly
    -0.44
     évêque
    -0.43
     life
    -0.40
    NSMutableArray
    -0.40
    POSITIVE LOGITS
    IntoConstraints
    0.94
    MigrationBuilder
    0.85
    RenderAtEndOf
    0.71
    ]")]
    0.68
     فريبيس
    0.67
    Enllaces
    0.67
    ValueStyle
    0.65
     GenerationType
    0.65
     ब्रेकडाउन
    0.64
     nahilalakip
    0.64
    Activations Density 0.088%

    No Known Activations