© 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. 33-GEMMASCOPE-RES-16K
    11. 2146
    Prev
    Next
    INDEX
    Explanations

    terms related to maintenance and prevention of operational issues in systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    足り
    -0.43
     MUR
    -0.41
     Desc
    -0.40
     magne
    -0.40
     Sorry
    -0.38
    Nhi
    -0.38
     Lots
    -0.37
    chila
    -0.37
     Савезне
    -0.37
     désolés
    -0.37
    POSITIVE LOGITS
     inneces
    0.84
     dzięki
    0.64
     berbahaya
    0.63
     graças
    0.61
    ďaka
    0.58
     penyebab
    0.58
     harmful
    0.57
     berlebihan
    0.56
     grâce
    0.56
     invasión
    0.56
    Activations Density 0.478%

    No Known Activations