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. 11778
    Prev
    Next
    INDEX
    Explanations

    terms related to market dynamics and competition

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

    Mention of the word "market."

    np_acts-logits-general · gemini-2.0-flash

    market statistics, value, share

    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
    fjspx
    -0.60
    ècie
    -0.58
     تضيفلها
    -0.57
    aime
    -0.56
    )_{
    -0.54
    TypeDef
    -0.53
    sos
    -0.50
    jspx
    -0.50
    ActionPerformed
    -0.50
     @"/
    -0.49
    POSITIVE LOGITS
    places
    1.02
    PLACE
    0.97
     place
    0.87
    Place
    0.83
    place
    0.81
    plaats
    0.71
    Markets
    0.68
     places
    0.67
     Drayton
    0.66
    Places
    0.65
    Activations Density 0.044%

    No Known Activations