© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 12639
    Prev
    Next
    INDEX
    Explanations

    mentions of staff members or personnel in various contexts

    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
     Tric
    -0.81
    Rien
    -0.74
     Zol
    -0.74
     XCTest
    -0.71
     Wikisource
    -0.71
     GLS
    -0.71
    LEncoder
    -0.70
     Modo
    -0.70
     RoutedEventArgs
    -0.70
     Tind
    -0.68
    POSITIVE LOGITS
     staff
    2.68
     Staff
    2.44
    Staff
    2.43
    staff
    2.33
     staffs
    2.20
     STAFF
    2.19
    STAFF
    2.06
     staffers
    1.51
     staffing
    1.51
     staf
    1.42
    Activations Density 0.041%

    No Known Activations