© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 4401
    Prev
    Next
    INDEX
    Explanations

    terms related to legal agreements and financial transactions

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

    Financial transactions, purchases, agreements, and contracts

    np_acts-logits-general · gemini-2.0-flash

    financial transactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jaardag
    -0.30
    립
    -0.29
     gri
    -0.28
     memberId
    -0.27
    ホルダー
    -0.27
     Aussch
    -0.27
     grid
    -0.26
     burn
    -0.26
    ανά
    -0.26
     نف
    -0.25
    POSITIVE LOGITS
     transaction
    1.16
     transactions
    1.00
     Transaction
    0.97
    transaction
    0.90
     deal
    0.89
     TRANSACTION
    0.87
     Transactions
    0.86
     сде
    0.86
    Transaction
    0.85
     transak
    0.82
    Activations Density 0.285%

    No Known Activations