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
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7995
    Prev
    Next
    INDEX
    Explanations

    references to financial costs and liabilities related to legal proceedings or transactions

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

    Legal and financial reimbursements and costs

    np_acts-logits-general · gemini-2.0-flash

    reimbursement of costs and expenses

    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
    SequentialGroup
    -0.51
     Saty
    -0.46
    labus
    -0.45
    ⤹
    -0.45
     betweenstory
    -0.44
     Dorothea
    -0.40
    PRWEB
    -0.40
     يتيمه
    -0.40
    delwed
    -0.40
    cagon
    -0.40
    POSITIVE LOGITS
     reimburse
    1.03
     costs
    1.02
     reimbursement
    0.99
     expense
    0.96
     cost
    0.92
    Costs
    0.89
    costs
    0.89
     reimbursed
    0.88
     Costs
    0.88
     expenses
    0.88
    Activations Density 0.349%

    No Known Activations