© 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. 22-GEMMASCOPE-RES-16K
    11. 15119
    Prev
    Next
    INDEX
    Explanations

    references to products or safety information related to medical or dietary items

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

    Phone numbers with "1-8" or "1-800"

    np_acts-logits-general · gemini-2.0-flash

    phone numbers and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kennung
    -0.48
    inheit
    -0.48
    getIn
    -0.47
    RUNNING
    -0.47
    In
    -0.47
    yot
    -0.46
    dersfield
    -0.45
     In
    -0.44
     fubject
    -0.44
     in
    -0.43
    POSITIVE LOGITS
    المناصب
    0.59
    دانشنامهٔ
    0.56
     protoimpl
    0.53
     adipis
    0.53
     CWE
    0.53
     immunization
    0.52
     regularization
    0.52
     Bentham
    0.49
     CITES
    0.47
    MongoClient
    0.46
    Activations Density 0.599%

    No Known Activations