© 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. 34-GEMMASCOPE-RES-16K
    11. 12668
    Prev
    Next
    INDEX
    Explanations

    phrases indicating movement or escape from a situation

    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
    RenderAtEndOf
    -0.68
    migrationBuilder
    -0.65
    Personensuche
    -0.58
    adaptiveStyles
    -0.57
    GEBURTS
    -0.56
     resourceCulture
    -0.55
     <>",
    -0.54
     EconPapers
    -0.53
     aapt
    -0.51
     AssemblyTitle
    -0.50
    POSITIVE LOGITS
     into
    0.39
     Stuhl
    0.36
    uce
    0.34
     stunt
    0.33
     onto
    0.33
    бки
    0.32
    pired
    0.32
    itaan
    0.32
     cser
    0.31
    tekend
    0.31
    Activations Density 0.103%

    No Known Activations