© 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
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 5975
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Ce" or its variations, which is indicative of a discussion in French or usage of the first person perspective in conversational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     renforcé
    -0.52
     graça
    -0.46
     uwagę
    -0.45
     Hoffnung
    -0.45
     París
    -0.44
     personnalisé
    -0.42
     renfor
    -0.42
     spalle
    -0.42
     cuarto
    -0.42
     diarios
    -0.42
    POSITIVE LOGITS
     cer
    0.96
    cer
    0.93
    Cer
    0.89
     CER
    0.87
     Ce
    0.87
     Cer
    0.85
     ce
    0.82
    CER
    0.82
    ceram
    0.81
     ceramic
    0.78
    Activations Density 0.185%

    No Known Activations