Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6495
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to chemical production processes and hydrocarbons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    doria
    -0.60
    UseVisualStyle
    -0.54
     salivary
    -0.54
    kset
    -0.52
    wdriver
    -0.52
    eryllium
    -0.51
     couverts
    -0.51
     Vivaldi
    -0.49
    marion
    -0.49
    geslacht
    -0.49
    POSITIVE LOGITS
     fuel
    1.62
     gasoline
    1.44
     Fuel
    1.39
     fuels
    1.38
     petrol
    1.35
    fuel
    1.34
    Fuel
    1.34
     oil
    1.27
     petroleum
    1.24
     Gasoline
    1.22
    Activations Density 0.157%

    No Known Activations