© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 21-GEMMASCOPE-RES-16K
    11. 16171
    Prev
    Next
    INDEX
    Explanations

    phrases related to customer service interactions and support

    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
    feitura
    -0.52
    DockStyle
    -0.51
     produisons
    -0.50
    wußt
    -0.50
    eckel
    -0.48
     चीज़ों
    -0.48
     HttpNotFound
    -0.48
     INTERESAR
    -0.48
    ObjectMeta
    -0.47
    warzys
    -0.46
    POSITIVE LOGITS
     customer
    1.74
     Customer
    1.59
     support
    1.49
    Customer
    1.40
     Support
    1.39
    customer
    1.36
    Support
    1.33
    support
    1.31
     CUSTOMER
    1.23
     helpline
    1.20
    Activations Density 0.208%

    No Known Activations