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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 2134
    Prev
    Next
    INDEX
    Explanations

    terms related to regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     *__
    -0.75
    mtd
    -0.61
    cerv
    -0.60
    tagHelper
    -0.59
     Picchu
    -0.58
     errand
    -0.58
    HPV
    -0.57
    DotNetBar
    -0.56
     Cristian
    -0.54
     psic
    -0.54
    POSITIVE LOGITS
     regulation
    2.82
     Regulation
    2.63
     REGULATION
    2.52
     regulated
    2.50
     regulate
    2.48
    Regulation
    2.45
     regulating
    2.36
    regulation
    2.34
     regulates
    2.26
     regulatory
    2.22
    Activations Density 0.091%

    No Known Activations