© 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. 20-GEMMASCOPE-RES-16K
    11. 15111
    Prev
    Next
    INDEX
    Explanations

    phrases related to functionality and efficiency in systems and processes

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

    Prepositions and conjunctions

    np_acts-logits-general · gemini-2.0-flash

    make Mac and iOS app development

    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
     myſelf
    -1.28
     Efq
    -1.25
     faſt
    -1.23
     purpoſe
    -1.18
     ſta
    -1.16
     ſche
    -1.13
     itſelf
    -1.13
     houſe
    -1.12
    UnsafeEnabled
    -1.12
     Theſe
    -1.12
    POSITIVE LOGITS
    Illuminate
    0.59
    <eos>
    0.56
      
    0.54
    JpaRepository
    0.49
    ...
    0.47
    webElementXpaths
    0.47
    jface
    0.47
     s
    0.45
     dé
    0.45
    ,
    0.45
    Activations Density 2.780%

    No Known Activations