© 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. 3-GEMMASCOPE-RES-16K
    11. 7915
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and terms related to multiplication and fractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Diweddarwch
    -0.61
    PreferredItem
    -0.61
     للاسماء
    -0.61
     ujednoznacz
    -0.56
    Externé
    -0.55
    يكب
    -0.53
    Externí
    -0.53
    дации
    -0.50
     فريبيس
    -0.49
     الحره
    -0.49
    POSITIVE LOGITS
    Multiply
    1.20
     multiplying
    1.20
     Multiply
    1.15
     multiply
    1.13
    multiply
    1.12
     multiplication
    1.08
     subtract
    1.01
     subtracting
    0.97
     multip
    0.97
    multip
    0.96
    Activations Density 0.646%

    No Known Activations