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. 20-GEMMASCOPE-RES-16K
    6. 11136
    Prev
    Next
    INDEX
    Explanations

    references to academic qualifications and professional roles

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

    Abbreviations (MIT, Dept, Juris, MBA)

    np_acts-logits-general · gemini-2.0-flash

    MIT business degrees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VIAF
    -0.66
     ddelweddau
    -0.65
    يميديا
    -0.62
     jScrollPane
    -0.60
    nesty
    -0.58
    Carriera
    -0.57
    deviantart
    -0.57
     OFDb
    -0.57
    bandcamp
    -0.56
     AssemblyProduct
    -0.56
    POSITIVE LOGITS
     business
    1.38
     Business
    1.37
    Business
    1.30
     MBA
    1.26
    business
    1.25
     BUSINESS
    1.12
    BUSINESS
    1.07
    MBA
    1.05
     management
    1.01
     Management
    0.99
    Activations Density 0.133%

    No Known Activations