© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 1068
    Prev
    Next
    INDEX
    Explanations

    terms related to sugary beverages and their consumption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OutputType
    -0.46
    HtmlAttribute
    -0.43
    öny
    -0.43
    ropshire
    -0.42
     Woolf
    -0.40
    ActionMode
    -0.40
     laude
    -0.39
     poêle
    -0.35
    SaveChangesAsync
    -0.35
    bentar
    -0.34
    POSITIVE LOGITS
     soda
    1.27
     Coke
    1.11
     Soda
    1.05
     Coca
    1.05
     Pepsi
    1.03
    soda
    1.02
     carbon
    1.01
    Coke
    1.00
     cola
    0.98
     Cola
    0.98
    Activations Density 0.248%

    No Known Activations