© 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. 0-GEMMASCOPE-RES-16K
    11. 7123
    Prev
    Next
    INDEX
    Explanations

    terms related to the properties and formulations of rubber and drum components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.77
     propOrder
    -0.73
     typelib
    -0.63
    OGND
    -0.62
    aarrggbb
    -0.59
    ftagPool
    -0.58
     BrowserModule
    -0.57
    webElementXpaths
    -0.55
     للاسماء
    -0.55
    addGap
    -0.54
    POSITIVE LOGITS
    listener
    0.61
    drum
    0.52
    Listener
    0.50
    drums
    0.49
     drum
    0.49
    Drum
    0.46
    uses
    0.46
     Drum
    0.44
    mean
    0.42
    Mean
    0.42
    Activations Density 0.165%

    No Known Activations