© 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. 5642
    Prev
    Next
    INDEX
    Explanations

    expressions of positivity and encouragement

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

    Followed by an affirmation

    np_acts-logits-general · gemini-2.0-flash

    is ok / fine / good / well

    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
    AddHtmlAttribute
    -0.73
    GEBURTSDATUM
    -0.60
    piram
    -0.59
    Tikang
    -0.58
    DeleteBehavior
    -0.57
     Мексичка
    -0.57
     raiſ
    -0.57
     themſelves
    -0.56
     tranſ
    -0.56
     تضيفلها
    -0.56
    POSITIVE LOGITS
     OK
    2.08
     ok
    2.08
     okay
    1.95
    OK
    1.73
    Ok
    1.73
     alright
    1.71
     Ok
    1.69
     fine
    1.65
    okay
    1.63
    ok
    1.56
    Activations Density 0.192%

    No Known Activations