© 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. 8131
    Prev
    Next
    INDEX
    Explanations

    references to celestial phenomena and their impact on perception or experience

    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
     autorytatywna
    -0.65
    RegressionTest
    -0.60
     CreateTagHelper
    -0.57
    تقاوى
    -0.57
    tanleria
    -0.56
     ujednoznacz
    -0.56
     lenker
    -0.51
     nahilalakip
    -0.51
     kasarigan
    -0.51
    ReusableCell
    -0.51
    POSITIVE LOGITS
     shadow
    2.61
     shadows
    2.17
    shadow
    2.17
     Shadow
    2.16
     shade
    2.16
     SHADOW
    2.06
    Shadow
    2.06
     shad
    1.84
     sombra
    1.84
    SHADOW
    1.83
    Activations Density 0.290%

    No Known Activations