© 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. 15309
    Prev
    Next
    INDEX
    Explanations

    references to upcoming events or updates

    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
     precedente
    -0.35
     предыду
    -0.33
     Einf
    -0.32
    Previous
    -0.31
     Previous
    -0.31
    ここまで
    -0.31
    previous
    -0.30
     penna
    -0.29
     tyle
    -0.28
     preceding
    -0.28
    POSITIVE LOGITS
     soon
    3.75
    soon
    3.16
    Soon
    3.13
     Soon
    3.03
     SOON
    2.75
     bientôt
    2.45
     snart
    2.36
     foon
    2.33
     shortly
    2.25
    很快
    1.88
    Activations Density 0.694%

    No Known Activations