© 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. 3-GEMMASCOPE-RES-16K
    11. 9044
    Prev
    Next
    INDEX
    Explanations

    Japanese particles and phrases related to asking for clarification or making requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    로운
    -0.32
     입니다
    -0.31
    ANEOUS
    -0.30
    ##
    -0.26
     perd
    -0.25
    입니다
    -0.25
    されました
    -0.25
     hvor
    -0.24
     cioè
    -0.23
    actual
    -0.23
    POSITIVE LOGITS
    transQ
    0.76
    ceğine
    0.75
    TProtocol
    0.71
    するの
    0.68
    HtmlAttribute
    0.66
     ſche
    0.65
    writeFieldEnd
    0.65
     nonUne
    0.64
    IntoConstraints
    0.64
    Vidite
    0.64
    Activations Density 0.791%

    No Known Activations