© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 22339
    Prev
    Next
    INDEX
    Explanations

    descriptive attributes of physical objects, particularly those that relate to safety and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.75
     fusca
    -0.73
    ="@+
    -0.66
    出版年
    -0.65
    viewDidLoad
    -0.65
     unplayable
    -0.63
    guisement
    -0.63
    sslich
    -0.63
     لينك
    -0.62
     geodes
    -0.61
    POSITIVE LOGITS
    Personensuche
    0.63
     pinulongan
    0.61
     designed
    0.53
     flexible
    0.52
    Skocz
    0.51
    chach
    0.51
     discreet
    0.49
    arschu
    0.48
     strategically
    0.47
     so
    0.47
    Activations Density 0.043%

    No Known Activations