© 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. 1-GEMMASCOPE-RES-16K
    6. 15684
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly dates or numerical references associated with historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.78
    SharedDtor
    -0.76
     insuffisamment
    -0.70
    httphttps
    -0.67
     MenuView
    -0.67
    SharedCtor
    -0.65
     seventies
    -0.65
    CodedInputStream
    -0.63
     فريبيس
    -0.62
     linkovi
    -0.61
    POSITIVE LOGITS
    almaz
    0.55
     ۱۸
    0.54
     FFFF
    0.54
    retrato
    0.53
    Forge
    0.53
     inalámb
    0.53
     gagner
    0.53
     chaînes
    0.53
     portátiles
    0.52
     urbanas
    0.52
    Activations Density 0.566%

    No Known Activations