© 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. 20-GEMMASCOPE-RES-16K
    6. 14908
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations, particularly regions labeled "West."

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

    "West" followed by a geographical location

    np_acts-logits-general · gemini-2.0-flash

    West followed by locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MeasureSpec
    -0.70
    JNIEnv
    -0.68
    OGND
    -0.67
    getahuan
    -0.65
     TextAppearance
    -0.64
     ModelExpression
    -0.62
    NameInMap
    -0.62
    SpringBootTest
    -0.60
    نجليز
    -0.59
    SBATCH
    -0.58
    POSITIVE LOGITS
    phal
    0.63
    cott
    0.60
     jScrollPane
    0.60
     Coast
    0.60
     Side
    0.56
    
    0.56
    pacs
    0.56
     timedelta
    0.54
     Indies
    0.54
     West
    0.54
    Activations Density 0.071%

    No Known Activations