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. 15621
    Prev
    Next
    INDEX
    Explanations

    references to the executive roles and positions in organizations

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

    Location following "at," "in," or "by"

    np_acts-logits-general · gemini-2.0-flash

    company or organization name

    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
     ioutil
    -0.64
    organised
    -0.64
    AndEndTag
    -0.64
    vellous
    -0.63
    ----</
    -0.62
    Enquiries
    -0.61
    TextHelper
    -0.60
     organised
    -0.60
     الرياضيه
    -0.59
     Initialise
    -0.59
    POSITIVE LOGITS
     Nashville
    0.66
     Midwest
    0.66
     Oklahoma
    0.65
     Missouri
    0.64
     statewide
    0.61
     nationwide
    0.60
     Indianapolis
    0.60
     Southeastern
    0.59
     Kansas
    0.59
     Louisiana
    0.58
    Activations Density 0.396%

    No Known Activations