© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8017
    Prev
    Next
    INDEX
    Explanations

    references to employees and personnel within a workplace context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     głę
    -0.41
     başlad
    -0.40
     tár
    -0.38
    неопр
    -0.38
    ună
    -0.36
     Beck
    -0.36
    wapV
    -0.35
     xadrez
    -0.35
     Depth
    -0.35
    withIdentifier
    -0.35
    POSITIVE LOGITS
     employees
    2.06
     workers
    1.68
    employees
    1.66
     Employees
    1.63
    Employees
    1.62
     EMPLOYEES
    1.48
     employes
    1.37
     staffers
    1.34
    workers
    1.26
     employés
    1.25
    Activations Density 0.164%

    No Known Activations