© 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. 28-GEMMASCOPE-RES-16K
    11. 9184
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to cultural events and celebrations

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

    Parades, processions, or marches

    np_acts-logits-general · gemini-2.0-flash

    parades and processions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maternidade
    -0.49
     carteira
    -0.46
     auriculares
    -0.42
     diting
    -0.41
     cafetería
    -0.40
     uñas
    -0.40
     estudar
    -0.40
     monasterio
    -0.38
     pondok
    -0.38
     suami
    -0.38
    POSITIVE LOGITS
     parade
    1.21
     parades
    1.13
     procession
    1.06
    parade
    1.04
     Parade
    1.02
     processions
    0.99
    Parade
    0.94
     marching
    0.84
     marched
    0.73
     celebrations
    0.72
    Activations Density 0.209%

    No Known Activations