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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 11284
    Prev
    Next
    INDEX
    Explanations

    references to customers and customer service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.94
     kasarigan
    -0.82
     gouache
    -0.75
    RenderAtEndOf
    -0.75
     telehealth
    -0.74
    ArrowToggle
    -0.73
    ✨:
    -0.73
    •••
    -0.73
     mergeFrom
    -0.72
    ctest
    -0.71
    POSITIVE LOGITS
     customer
    2.46
     customers
    2.34
     Customer
    2.22
     Customers
    2.15
    Customer
    2.08
    customer
    2.06
    Customers
    1.99
     getCustomer
    1.96
    customers
    1.96
     CUSTOMER
    1.91
    Activations Density 0.032%

    No Known Activations