© 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. 3393
    Prev
    Next
    INDEX
    Explanations

    phrases and commands related to setting up web application routes and views in a programming context

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

    Follows "add" or a period

    np_acts-logits-general · gemini-2.0-flash

    adding routes or views

    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
     للمعارف
    -0.84
    Према
    -0.74
    extAlignment
    -0.68
    ChildScrollView
    -0.67
    SceneManagement
    -0.65
    
    -0.65
     Waray
    -0.64
    TestTools
    -0.62
    protoimpl
    -0.61
     Putnam
    -0.61
    POSITIVE LOGITS
     Gulf
    0.52
    Flask
    0.51
     flask
    0.51
    ृत
    0.48
     sqlalchemy
    0.48
    Gulf
    0.47
    flask
    0.47
     Flask
    0.46
     Петро
    0.46
    lask
    0.46
    Activations Density 0.054%

    No Known Activations