© 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. 14934
    Prev
    Next
    INDEX
    Explanations

    connections between causative phrases and their effects

    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
     незавершена
    -0.63
     يتيمه
    -0.56
     otomatig
    -0.53
     للاسماء
    -0.51
     فريبيس
    -0.50
    isContained
    -0.48
     Audiodateien
    -0.48
     useAppContext
    -0.45
     Plenty
    -0.44
     McCar
    -0.44
    POSITIVE LOGITS
     finally
    0.72
     ultimately
    0.67
     lastly
    0.63
     respectively
    0.61
     moreover
    0.60
     indeed
    0.60
     finalmente
    0.59
     successively
    0.59
    finally
    0.58
     firstly
    0.57
    Activations Density 1.281%

    No Known Activations