© 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. 24-GEMMASCOPE-RES-16K
    11. 5104
    Prev
    Next
    INDEX
    Explanations

    specific phrases and structures relating to quantities or positions in the text

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

    "way" after certain words

    np_acts-logits-general · gemini-2.0-flash

    ways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twimg
    -0.80
    MessageTagHelper
    -0.72
     Meksiku
    -0.71
     ivelany
    -0.69
     насељу
    -0.68
    Становништво
    -0.65
    Personensuche
    -0.65
    новниш
    -0.64
     AssemblyCulture
    -0.64
    Jeografia
    -0.63
    POSITIVE LOGITS
     way
    4.58
    way
    3.47
    Way
    3.35
     Way
    3.27
     WAY
    3.13
    WAY
    2.93
     ways
    2.93
    ways
    2.47
     Ways
    2.25
    Ways
    2.24
    Activations Density 0.644%

    No Known Activations