© 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. 1337
    Prev
    Next
    INDEX
    Explanations

    structured data representations such as lists and dictionaries

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

    "Tuesday" or similar day-related terms

    np_acts-logits-general · gemini-2.0-flash

    days of the week and numbers

    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
    sizeCache
    -0.80
     fifth
    -0.69
     lenker
    -0.68
     sixth
    -0.67
    WebVitals
    -0.66
     seventh
    -0.64
     pią
    -0.64
     five
    -0.63
     Friday
    -0.63
    OGND
    -0.63
    POSITIVE LOGITS
     Tuesday
    0.63
    Tuesday
    0.59
     Selasa
    0.58
     TUESDAY
    0.56
     Tuesdays
    0.52
    2
    0.49
     tuesday
    0.49
     Two
    0.48
    Tues
    0.47
     Tweede
    0.47
    Activations Density 0.059%

    No Known Activations