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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 7616
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "les" and its variations or forms in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    -0.38
     sac
    -0.38
     sector
    -0.35
    B
    -0.35
     boî
    -0.32
    the
    -0.32
    e
    -0.32
    M
    -0.32
    1
    -0.31
     Dorm
    -0.31
    POSITIVE LOGITS
    jenigen
    0.87
     kasarigan
    0.85
     beiden
    0.82
     meisten
    0.81
    queles
    0.81
     meeste
    0.77
     dignité
    0.75
     meille
    0.74
    demás
    0.73
     istrinya
    0.73
    Activations Density 0.038%

    No Known Activations