© 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. 7169
    Prev
    Next
    INDEX
    Explanations

    statistical terms and analysis related to data processing and modeling

    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
    principalColumn
    -0.45
     Behr
    -0.36
     conozco
    -0.35
     ويكيميديا
    -0.35
    tagext
    -0.35
    endorong
    -0.35
     Groves
    -0.34
    TITUDE
    -0.34
    跪
    -0.34
     عم
    -0.33
    POSITIVE LOGITS
     entropy
    0.67
     spectrum
    0.57
    rungsseite
    0.57
     fractal
    0.56
    熵
    0.55
     BoxFit
    0.55
     spectra
    0.54
     Entropy
    0.52
    #![
    0.52
    expandindo
    0.52
    Activations Density 2.076%

    No Known Activations