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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 8705
    Prev
    Next
    INDEX
    Explanations

    terms related to audit quality and financial accountability

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

    auditing and auditors

    np_acts-logits-general · gemini-2.0-flash

    audit quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ddelweddau
    -0.66
     متحده
    -0.62
     Référence
    -0.58
    RLock
    -0.56
     getItemCount
    -0.56
    談社
    -0.54
    urlencoded
    -0.53
    rénées
    -0.52
    ğren
    -0.49
    WebServlet
    -0.48
    POSITIVE LOGITS
     accounting
    0.90
     audit
    0.90
     Accounting
    0.88
    Accounting
    0.85
     auditors
    0.85
     accountants
    0.85
     Audit
    0.84
     Accountants
    0.84
     Accountant
    0.83
     accountant
    0.82
    Activations Density 0.088%

    No Known Activations