© 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. 9-GEMMASCOPE-RES-16K
    11. 9612
    Prev
    Next
    INDEX
    Explanations

    mentions of infrequent or rare events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oa̍t
    -0.38
    İstinadlar
    -0.34
     bezeichneter
    -0.34
    Fastest
    -0.33
     faſt
    -0.33
     ſta
    -0.33
     Chriſt
    -0.32
     молод
    -0.32
     youngest
    -0.32
     atrop
    -0.32
    POSITIVE LOGITS
     occasional
    1.49
     occasionally
    1.34
     Occasional
    1.30
     Occasionally
    1.27
    occas
    1.23
    occasion
    1.22
    Occasionally
    1.20
    偶尔
    1.17
     sporad
    1.16
     sporadic
    1.14
    Activations Density 0.519%

    No Known Activations