© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11221
    Prev
    Next
    INDEX
    Explanations

    references to geographical regions and ethnic groups

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

    Follows "and" or a punctuation mark

    np_acts-logits-general · gemini-2.0-flash

    connecting list items

    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
     email
    -1.08
    Email
    -1.02
     Email
    -0.96
    email
    -0.91
     emails
    -0.89
     eggs
    -0.88
     emailing
    -0.87
     edit
    -0.86
     egg
    -0.84
     election
    -0.83
    POSITIVE LOGITS
    ="@+
    0.65
    脚注の使い方
    0.55
    mergeFrom
    0.54
    runOnUiThread
    0.52
    tershire
    0.52
    WebVitals
    0.51
    myspace
    0.50
     الدولى
    0.50
     saites
    0.49
     صوتيه
    0.49
    Activations Density 0.292%

    No Known Activations