© 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. 0-GEMMASCOPE-RES-65K
    6. 9561
    Prev
    Next
    INDEX
    Explanations

    references to financial transactions and refunds, particularly in the context of coronary health-related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteBarrier
    -0.74
    ///</
    -0.60
    httphttps
    -0.60
    円で
    -0.60
    kloped
    -0.59
    ddha
    -0.58
    grà
    -0.57
    િક
    -0.57
    fjspx
    -0.56
    baomidou
    -0.56
    POSITIVE LOGITS
    enumi
    0.94
     refund
    0.86
     refunds
    0.81
     refunded
    0.75
    refund
    0.70
     rebate
    0.68
    imbursement
    0.68
    География
    0.66
     reimbursed
    0.66
     reimbursement
    0.66
    Activations Density 0.051%

    No Known Activations