© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 14567
    Prev
    Next
    INDEX
    Explanations

    references to traditional celebrations and cultural events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ictwo
    -0.37
     paznok
    -0.35
     doğum
    -0.32
    Tikang
    -0.32
    最快更新
    -0.31
    Raum
    -0.30
     pondok
    -0.30
     cueva
    -0.30
     اتاق
    -0.29
    govine
    -0.29
    POSITIVE LOGITS
     parade
    1.72
     procession
    1.63
     parades
    1.48
     Parade
    1.45
    parade
    1.43
     processions
    1.40
    Parade
    1.39
     marching
    1.38
     march
    1.30
     marched
    1.23
    Activations Density 0.253%

    No Known Activations