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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 12515
    Prev
    Next
    INDEX
    Explanations

    phrases and contexts related to support and community actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IndentedString
    -0.87
     صوتيه
    -0.85
    AddTagHelper
    -0.85
    ArgsConstructor
    -0.84
     يتيمه
    -0.78
    writeFieldEnd
    -0.78
    makeConstraints
    -0.76
     nahilalakip
    -0.74
     StatefulWidget
    -0.74
     itſelf
    -0.72
    POSITIVE LOGITS
     menyambut
    0.75
     welcome
    0.57
     welcoming
    0.57
     waiting
    0.54
     welcomes
    0.52
     greet
    0.51
     đón
    0.50
     greeted
    0.50
     greets
    0.49
     awaiting
    0.49
    Activations Density 0.338%

    No Known Activations