© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5485
    Prev
    Next
    INDEX
    Explanations

    references to specific case details and legal standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -1.25
     Савезне
    -1.22
    bootstrapcdn
    -1.21
    LookAnd
    -1.20
    NameInMap
    -1.17
     wireType
    -1.14
     فريبيس
    -1.12
     cherchés
    -1.09
     Мексичка
    -1.09
     onAnimation
    -1.07
    POSITIVE LOGITS
    ↵↵
    0.95
    .
    0.79
    <eos>
    0.70
    ,
    0.70
    ↵
    0.64
      
    0.62
     
    0.60
    !
    0.58
    [toxicity=0]
    0.58
    -
    0.57
    Activations Density 0.179%

    No Known Activations