© 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. 7040
    Prev
    Next
    INDEX
    Explanations

    topics related to healthcare and visiting various places or events

    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
    verbrauch
    -0.38
     consommer
    -0.35
     design
    -0.35
     consumption
    -0.34
    хіво
    -0.32
     consumed
    -0.32
     columns
    -0.32
     remains
    -0.32
     flows
    -0.32
     designs
    -0.31
    POSITIVE LOGITS
     visiting
    0.93
    Visiting
    0.89
    visiting
    0.83
     Visiting
    0.82
     visit
    0.75
    visit
    0.73
     VISIT
    0.71
    makeText
    0.71
     Touring
    0.70
     visitor
    0.69
    Activations Density 1.398%

    No Known Activations