© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 8206
    Prev
    Next
    INDEX
    Explanations

    emotions and expressions of sadness or frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.81
    rungsseite
    -0.70
    Personensuche
    -0.68
     surla
    -0.66
    ➯
    -0.65
     referenties
    -0.64
     wireType
    -0.63
    SuccessListener
    -0.62
    matchCondition
    -0.60
     Paglinawan
    -0.60
    POSITIVE LOGITS
     :(
    1.61
     :-(
    1.37
     :'(
    1.30
     :/
    1.27
    :(
    1.23
     ;(
    1.15
     😔
    1.14
     😢
    1.13
     =(
    1.09
     😭
    1.05
    Activations Density 0.312%

    No Known Activations