© 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. 3710
    Prev
    Next
    INDEX
    Explanations

    phrases related to reducing problems or processes

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

    Phrases with "boil down to" or "reduce to"

    np_acts-logits-general · gemini-2.0-flash

    boil down to / reduces to

    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
    البته
    -0.52
     <>",
    -0.51
    Disagree
    -0.50
    //
    -0.49
    كذا
    -0.48
    τικο
    -0.47
     Rocca
    -0.47
     GlobalKey
    -0.47
    [++
    -0.46
    intios
    -0.46
    POSITIVE LOGITS
     boils
    1.45
     boil
    1.28
     boiled
    1.21
     reduced
    1.17
     Reduced
    1.03
    Reduced
    1.00
     reduce
    1.00
     reduces
    0.97
     narrowed
    0.97
    reduced
    0.97
    Activations Density 0.434%

    No Known Activations