© 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. 8400
    Prev
    Next
    INDEX
    Explanations

    interactive or conversational prompts and questions directed towards the reader

    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
    __':
    -0.77
     مشين
    -0.69
    __":
    -0.68
     MainAxisSize
    -0.66
    __':
    -0.66
    RectangleBorder
    -0.63
    __":
    -0.60
    istoitu
    -0.58
     שוליים
    -0.56
    <!--[
    -0.54
    POSITIVE LOGITS
    Idk
    0.57
     bruh
    0.55
     roblox
    0.54
     Idk
    0.54
     Roblox
    0.51
     ;-;
    0.49
     cuz
    0.49
    Bruh
    0.49
    Anyways
    0.48
     wattpad
    0.48
    Activations Density 0.342%

    No Known Activations