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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 5144
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and distances associated with locations

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

    Distance or length measurements

    np_acts-logits-general · gemini-2.0-flash

    distance units (miles, km)

    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
     թվական
    -0.64
     autorytatywna
    -0.60
    Referencer
    -0.59
    NOPQRST
    -0.56
    әрмәләр
    -0.56
    RenderAtEndOf
    -0.53
    ứng
    -0.51
    Lähteet
    -0.51
     slope
    -0.51
    цездатний
    -0.51
    POSITIVE LOGITS
     miles
    1.10
    Miles
    1.00
     MILES
    0.99
     Miles
    0.99
    miles
    0.98
     kilometers
    0.91
     mileage
    0.91
     km
    0.90
     kilometres
    0.89
     mile
    0.88
    Activations Density 0.114%

    No Known Activations