© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 8242
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Juday" or variations of it in various contexts

    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
     الرياضيه
    -0.37
    štění
    -0.35
     skippy
    -0.35
     Lagi
    -0.35
     culto
    -0.34
    outside
    -0.34
     Abfall
    -0.33
    concern
    -0.33
     negociaciones
    -0.33
    primera
    -0.33
    POSITIVE LOGITS
    DockStyle
    0.54
     Bud
    0.54
    dAtA
    0.52
    Bud
    0.52
     bud
    0.52
    unknownFields
    0.52
    ArgumentParser
    0.51
    JNIEnv
    0.50
     BUD
    0.50
     cud
    0.48
    Activations Density 0.195%

    No Known Activations