© 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. 38-GEMMASCOPE-RES-16K
    11. 14172
    Prev
    Next
    INDEX
    Explanations

    references to bottle caps and sealing mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Erreferentziak
    -0.48
    GEBURTSDATUM
    -0.47
     énon
    -0.40
    gehenden
    -0.38
     doInBackground
    -0.38
    rawData
    -0.38
    JMenu
    -0.37
    Résumé
    -0.37
    resultMap
    -0.36
     linkovi
    -0.36
    POSITIVE LOGITS
     bottle
    1.82
     bottles
    1.69
    bottle
    1.53
     Bottle
    1.51
     Bottles
    1.48
    Bottle
    1.44
     BOTT
    1.40
    bottles
    1.37
    瓶
    1.29
     botella
    1.27
    Activations Density 0.277%

    No Known Activations