© 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. 28-GEMMASCOPE-RES-16K
    11. 4089
    Prev
    Next
    INDEX
    Explanations

    references to companies and their activities, particularly in relation to contracts and the pharmaceutical industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Word before "Company" (or similar business entities)

    np_acts-logits-general · gemini-2.0-flash

    company

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.41
     defaultstate
    -0.39
    Invent
    -0.35
    SuppressLint
    -0.34
    mas
    -0.33
    InputBorder
    -0.31
    oster
    -0.31
     هن
    -0.31
    bor
    -0.31
     chemistry
    -0.30
    POSITIVE LOGITS
     company
    1.38
     Company
    1.19
    company
    1.13
    公司
    1.08
    Company
    1.07
     compañía
    1.02
     COMPANY
    1.02
     corporation
    1.00
     companies
    0.98
     empresa
    0.97
    Activations Density 0.605%

    No Known Activations