© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 2742
    Prev
    Next
    INDEX
    Explanations

    terms related to audits and their outcomes

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

    accounting audits and firms

    np_acts-logits-general · gemini-2.0-flash

    audit and accounting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebServlet
    -0.68
     StringTokenizer
    -0.67
     متحده
    -0.66
     ddelweddau
    -0.61
    Redirection
    -0.59
    WriteTagHelper
    -0.58
    HtmlAttribute
    -0.56
     Référence
    -0.55
     lethal
    -0.53
     revend
    -0.51
    POSITIVE LOGITS
     accounting
    1.03
     Accounting
    1.00
     audit
    0.98
    Accounting
    0.95
     accountant
    0.94
     accountants
    0.93
     auditing
    0.92
     Auditing
    0.87
     Audit
    0.85
     Accountants
    0.84
    Activations Density 0.239%

    No Known Activations