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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 6040
    Prev
    Next
    INDEX
    Explanations

    references to property and related concepts in legal and financial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     colorés
    -0.91
    Према
    -0.84
    quelles
    -0.84
     dénon
    -0.82
    committees
    -0.82
     aveug
    -0.81
    GEBURTS
    -0.81
     mẽ
    -0.80
     MainAxisSize
    -0.80
     дописавши
    -0.78
    POSITIVE LOGITS
     property
    1.94
     properties
    1.83
     Property
    1.70
    getProperty
    1.64
    property
    1.63
    Property
    1.61
     getProperty
    1.58
     Properties
    1.57
     PROPERTY
    1.55
    properties
    1.54
    Activations Density 0.047%

    No Known Activations