© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29551
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terms and property regulations

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

    combining, grouping, or uniting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Eng
    -0.41
    一切都
    -0.41
    絶
    -0.40
    ExecutionContext
    -0.39
    engage
    -0.39
     ENG
    -0.37
    InnerText
    -0.36
     patrimonio
    -0.36
    arc
    -0.35
    diente
    -0.35
    POSITIVE LOGITS
     together
    1.19
     grouped
    1.05
    Together
    1.02
    together
    1.01
     TOGETHER
    1.00
     united
    0.99
     Together
    0.98
     pooled
    0.98
     grouping
    0.97
     combined
    0.97
    Activations Density 0.323%

    No Known Activations