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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13059
    Prev
    Next
    INDEX
    Explanations

    terms related to legal compliance and regulations

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

    Legal compliance and regulations

    np_acts-logits-general · gemini-2.0-flash

    laws and regulations compliance

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    CloseOperation
    -0.53
    delwed
    -0.46
     yyj
    -0.43
    ImageContext
    -0.42
    WriteTagHelper
    -0.41
     AssemblyTitle
    -0.40
    قایناق‌لار
    -0.40
    sunt
    -0.39
     ویکی‌پدیا
    -0.39
     initComponents
    -0.39
    POSITIVE LOGITS
     compliance
    0.78
     Compliance
    0.72
    compliance
    0.70
    Compliance
    0.65
     compliant
    0.62
    compliant
    0.61
     conformité
    0.58
     complied
    0.57
     Compliant
    0.55
     compli
    0.53
    Activations Density 0.235%

    No Known Activations