© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 33-GEMMASCOPE-RES-16K
    11. 11491
    Prev
    Next
    INDEX
    Explanations

    concerns related to data deletion and recovery processes

    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
     DbSet
    -0.41
     Rick
    -0.39
     Hartford
    -0.37
     Kentucky
    -0.37
     Wickham
    -0.37
    fileupload
    -0.36
    RestTemplate
    -0.36
     Hendrick
    -0.36
    Kentucky
    -0.36
    茨城
    -0.36
    POSITIVE LOGITS
     Apple
    1.17
    Apple
    1.11
     apple
    1.11
     Macs
    1.06
     Mac
    1.06
    Mac
    1.03
     macOS
    1.01
     MacOS
    0.98
     Apples
    0.97
     iMac
    0.97
    Activations Density 0.720%

    No Known Activations