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

    Neuronpedia

    APICircuit 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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1147
    Prev
    Next
    INDEX
    Explanations

    references to customer data and related database operations

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

    elements related to customer management and subscription processes

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

    sales customer

    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
     Rai
    -0.58
     Maia
    -0.57
     Audiodateien
    -0.55
     hallway
    -0.54
    Syntax
    -0.54
     Corridor
    -0.54
     bio
    -0.53
     Mohan
    -0.52
    orne
    -0.52
     Hall
    -0.51
    POSITIVE LOGITS
     customer
    2.03
     Customer
    1.86
    customer
    1.84
    Customer
    1.72
     CUSTOMER
    1.71
     getCustomer
    1.67
     customers
    1.65
    getCustomer
    1.59
    CUSTOMER
    1.55
    ustomer
    1.52
    Activations Density 0.031%

    No Known Activations