© 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. 11790
    Prev
    Next
    INDEX
    Explanations

    elements related to programming or technical discussions, particularly involving commands and expressions

    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
     took
    -0.77
    took
    -0.74
     went
    -0.69
     gave
    -0.64
     furent
    -0.61
     broke
    -0.59
    went
    -0.59
     did
    -0.58
     became
    -0.58
     firent
    -0.58
    POSITIVE LOGITS
     می‌
    0.48
     &___
    0.46
     decía
    0.45
     fazia
    0.44
    новништво
    0.40
    twimg
    0.39
     Provo
    0.39
     Era
    0.39
     daba
    0.39
     era
    0.39
    Activations Density 0.155%

    No Known Activations