© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11199
    Prev
    Next
    INDEX
    Explanations

    key historical events and significant inventions

    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
     constantemente
    -0.29
     conversar
    -0.28
    笑了笑
    -0.28
    ++]=
    -0.28
    unnitel
    -0.27
     Ergänzung
    -0.26
     trabajado
    -0.25
     pensado
    -0.25
     mål
    -0.24
     enfo
    -0.24
    POSITIVE LOGITS
     paved
    1.27
     paving
    1.24
     usher
    1.20
     pave
    1.14
     ushered
    1.09
     heral
    1.04
     inaugur
    1.02
     marking
    1.02
     inaugurate
    0.96
    開啟
    0.95
    Activations Density 0.734%

    No Known Activations