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. 6-GEMMASCOPE-RES-16K
    6. 13525
    Prev
    Next
    INDEX
    Explanations

    terms related to workplace dynamics and employee interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.84
     CreateTagHelper
    -0.82
     تضيفلها
    -0.78
    󠁢
    -0.72
     Signalez
    -0.70
     Wiktionnaire
    -0.67
    évaluateur
    -0.67
     estimés
    -0.65
     Audiodateien
    -0.65
    GEBURTSDATUM
    -0.65
    POSITIVE LOGITS
     staff
    0.98
     employees
    0.88
     Staff
    0.87
     employee
    0.85
    Employees
    0.82
    Staff
    0.81
     Employees
    0.81
     karyawan
    0.80
    staff
    0.76
    Employee
    0.73
    Activations Density 0.482%

    No Known Activations