© 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. 14421
    Prev
    Next
    INDEX
    Explanations

    conjectural statements or thoughts expressing uncertainty

    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
     teda
    -0.42
     hoping
    -0.39
     teniendo
    -0.35
    さすがに
    -0.34
     étant
    -0.33
    虽说
    -0.32
     persönlichen
    -0.32
     while
    -0.32
     raczej
    -0.32
    自分は
    -0.31
    POSITIVE LOGITS
     look
    1.69
     Look
    1.61
    Look
    1.60
    look
    1.59
     LOOK
    1.38
     imagine
    1.28
     listen
    1.26
    LOOK
    1.25
     remember
    1.20
    你看
    1.18
    Activations Density 0.432%

    No Known Activations