© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 456
    Prev
    Next
    INDEX
    Explanations

    phrases related to costs, burdens, and prices associated with actions or mechanisms

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

    phrases related to costs and benefits associated with mechanisms or processes

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

    price or cost

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     snippetHide
    -0.49
    StringVar
    -0.46
    WebServlet
    -0.46
     catholique
    -0.46
     StringVar
    -0.45
    ViewById
    -0.45
    ResumeLayout
    -0.45
    łaści
    -0.44
     soutenu
    -0.44
     réfugi
    -0.42
    POSITIVE LOGITS
     price
    1.76
    price
    1.50
     Price
    1.45
     PRICE
    1.43
    Price
    1.41
     cost
    1.36
     prezzo
    1.34
     preço
    1.31
     paying
    1.27
     precio
    1.27
    Activations Density 0.132%

    No Known Activations