Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11670
    Prev
    Next
    INDEX
    Explanations

    terms related to auditing, accounting, and market regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.50
     مرئيه
    -0.47
     كومونز
    -0.47
     lòng
    -0.44
    terie
    -0.41
    IBarButtonItem
    -0.40
    rungsseite
    -0.40
     ContentValues
    -0.40
     CreateTagHelper
    -0.39
    adə
    -0.39
    POSITIVE LOGITS
     Accounting
    0.80
    Accounting
    0.78
     accounting
    0.77
     accountant
    0.72
     бухгал
    0.71
     accountants
    0.68
    accounting
    0.65
     Accountant
    0.64
     Accountants
    0.63
     financial
    0.60
    Activations Density 0.247%

    No Known Activations