© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4243
    Prev
    Next
    INDEX
    Explanations

    mechanical specifications and condition-related descriptors of vehicles

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

    Units of distance or time measurement

    np_acts-logits-general · gemini-2.0-flash

    miles and kilometers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.88
    issner
    -0.75
    IsContent
    -0.72
     actionMode
    -0.68
    KURZBESCHREIBUNG
    -0.67
     snippetHide
    -0.65
    phrine
    -0.64
    (!__
    -0.63
    XMLSchema
    -0.62
    enderror
    -0.62
    POSITIVE LOGITS
     mileage
    1.04
     mila
    0.81
     miles
    0.78
     Mileage
    0.77
     kilometers
    0.70
    mileage
    0.68
     kilometres
    0.68
    Mileage
    0.66
    miles
    0.63
     kilometer
    0.62
    Activations Density 0.078%

    No Known Activations