Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1579
    Prev
    Next
    INDEX
    Explanations

    conversational expressions and statements related to setting up businesses

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

    Preceding words of "business"

    np_acts-logits-general · gemini-2.0-flash

    business status and operations

    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
     polaire
    -0.56
    xffffffff
    -0.54
    thenReturn
    -0.54
     billions
    -0.51
    Descarga
    -0.50
    ouwen
    -0.49
    aarrggbb
    -0.49
    </tfoot>
    -0.49
     scientists
    -0.49
    ίος
    -0.48
    POSITIVE LOGITS
     business
    1.26
     customers
    1.11
    business
    1.02
     Customers
    0.96
     Business
    0.95
     clientele
    0.95
    Business
    0.94
    Customers
    0.94
     BUSINESS
    0.92
    customers
    0.89
    Activations Density 0.350%

    No Known Activations