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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 848
    Prev
    Next
    INDEX
    Explanations

    terms related to lending and borrowing

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

    lending and borrowing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.59
    setVerticalGroup
    -0.51
    BindingResult
    -0.50
    SocketChannel
    -0.49
    Erstellt
    -0.48
     SqlCommand
    -0.48
    òa
    -0.47
     BoxFit
    -0.47
    didSet
    -0.45
     ivelany
    -0.45
    POSITIVE LOGITS
     loaned
    1.17
     borrowed
    1.12
     borrow
    1.02
     loan
    1.01
     borrowing
    1.00
     BORROW
    0.98
    borrow
    0.94
     Borrow
    0.94
    Borrow
    0.94
     Loan
    0.91
    Activations Density 0.019%

    No Known Activations