© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 9751
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to internal combustion engines and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Internal combustion engine characteristics

    np_acts-logits-general · gemini-2.0-flash

    internal combustion engine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.62
     Wikispecies
    -0.57
     Gelder
    -0.53
     lipat
    -0.48
     Pelham
    -0.48
    antenna
    -0.48
    liothèque
    -0.47
    astéroïdes
    -0.47
    뎁
    -0.47
     télé
    -0.46
    POSITIVE LOGITS
     engine
    1.27
     Engine
    1.19
     combustion
    1.14
     diesel
    1.10
     Diesel
    1.09
     engines
    1.08
     fuel
    1.07
     ENGINE
    1.05
    Diesel
    1.01
    engine
    1.00
    Activations Density 0.302%

    No Known Activations