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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 8608
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to employment and worker classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CodedInputStream
    -0.32
    canestro
    -0.32
     azt
    -0.32
    Попис
    -0.30
    adam
    -0.29
    rister
    -0.29
     BorderRadius
    -0.28
    TestingModule
    -0.28
    ValueStyle
    -0.28
    ecken
    -0.27
    POSITIVE LOGITS
     employees
    2.67
     employee
    2.59
     Employees
    2.27
    Employees
    2.25
    employee
    2.23
    employees
    2.19
     Employee
    2.17
    Employee
    2.16
     EMPLOYEES
    2.08
     EMPLOYEE
    2.05
    Activations Density 0.379%

    No Known Activations