© 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. 3-GEMMASCOPE-RES-16K
    11. 6537
    Prev
    Next
    INDEX
    Explanations

    terms related to storage processes and overnight durations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SizeF
    -0.54
    DockStyle
    -0.52
    Carriera
    -0.51
    ultra
    -0.47
    httphttps
    -0.46
    advantage
    -0.44
     Erwä
    -0.43
    ərbaycan
    -0.42
    easier
    -0.42
     onOptions
    -0.42
    POSITIVE LOGITS
    store
    0.94
    STORE
    0.83
    Store
    0.72
     supermarket
    0.68
     Supermarket
    0.61
     supermarkets
    0.61
    Pharmacy
    0.59
     pharmacy
    0.58
    pharmacy
    0.58
     grocery
    0.57
    Activations Density 0.218%

    No Known Activations