© 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. 16149
    Prev
    Next
    INDEX
    Explanations

    questions related to choices and guidance

    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
     Obrador
    -0.63
    msgSender
    -0.56
    يكب
    -0.55
     again
    -0.54
    Again
    -0.52
     Again
    -0.52
    >--}}
    -0.52
    一提
    -0.49
    美味しかったです
    -0.49
     eventual
    -0.49
    POSITIVE LOGITS
    Below
    1.09
     Below
    1.05
     Here
    0.97
    Here
    0.94
     below
    0.93
     here
    0.90
     voici
    0.90
     Voici
    0.88
     berikut
    0.88
    そこで
    0.86
    Activations Density 0.477%

    No Known Activations