Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 493
    Prev
    Next
    INDEX
    Explanations

    terms related to the shipping and logistics industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wachs
    -0.55
     Habit
    -0.54
    PerformLayout
    -0.52
    netbeans
    -0.52
     élector
    -0.51
    MenuInflater
    -0.49
    BATH
    -0.48
    habit
    -0.48
    mybatisplus
    -0.47
     IUPAC
    -0.47
    POSITIVE LOGITS
     freight
    1.71
     cargo
    1.64
     shipping
    1.58
     shipper
    1.56
     shippers
    1.56
     shipment
    1.51
     transport
    1.50
     Freight
    1.48
     transporting
    1.47
     shipments
    1.42
    Activations Density 0.371%

    No Known Activations