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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 1264
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to rights, protections, and conditions of individuals within the judicial system

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

    after "to"

    np_acts-logits-general · gemini-2.0-flash

    incentive and encourage

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     laude
    -0.53
    bootstrapcdn
    -0.52
     queima
    -0.49
    approche
    -0.48
    ukone
    -0.47
     moeite
    -0.47
     montaje
    -0.47
     @{
    -0.47
     decoradas
    -0.46
     חיצוניים
    -0.46
    POSITIVE LOGITS
    PerformLayout
    0.79
     incentive
    0.77
    SizeMode
    0.73
     مشارکت‌کنندگان
    0.72
    WriteTagHelper
    0.70
     encourage
    0.67
     incentiv
    0.64
     incentives
    0.64
     encouraging
    0.61
     encourages
    0.59
    Activations Density 0.541%

    No Known Activations