© 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. 5-GEMMASCOPE-RES-16K
    11. 6707
    Prev
    Next
    INDEX
    Explanations

    phrases related to applications of laws or rules in legal contexts

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

    phrases indicating legal or regulatory applications of specific laws or doctrines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.88
    AndEndTag
    -0.71
    ंदीखरीदारी
    -0.68
    IsMutable
    -0.64
     defaultstate
    -0.61
    GEBURTSDATUM
    -0.60
    Carriera
    -0.60
    CardHeader
    -0.58
    TypedDataSet
    -0.58
    eclipse
    -0.56
    POSITIVE LOGITS
     applied
    1.74
    applied
    1.61
     application
    1.57
     apply
    1.55
     applying
    1.55
     Applied
    1.53
    Applied
    1.53
     Apply
    1.48
    Applying
    1.43
     Applying
    1.43
    Activations Density 0.221%

    No Known Activations