© 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. 35-GEMMASCOPE-RES-16K
    11. 13298
    Prev
    Next
    INDEX
    Explanations

    references to vacuum-related products and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TokenNameLBRACE
    -0.46
    
    -0.46
     Lut
    -0.45
    addContainerGap
    -0.44
    IntoConstraints
    -0.43
     JSONException
    -0.40
    InsertCommand
    -0.40
    fillType
    -0.40
    GEBURTSDATUM
    -0.40
    MIDDLEWARE
    -0.39
    POSITIVE LOGITS
     vacuum
    2.17
     Vacuum
    1.87
    Vacuum
    1.84
    vacuum
    1.82
     vacu
    1.79
     vac
    1.72
     Vac
    1.55
     VAC
    1.48
    vac
    1.48
    真空
    1.48
    Activations Density 0.273%

    No Known Activations