© 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. 17254
    Prev
    Next
    INDEX
    Explanations

    markers or headings that indicate the beginning of a new section or important context in a document

    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
    queryInterface
    -0.54
    iramente
    -0.53
    cties
    -0.52
    NgModule
    -0.51
    AnchorStyles
    -0.50
     sigh
    -0.50
    ोड़
    -0.49
    حد
    -0.47
    ]='\
    -0.47
    ]--;
    -0.47
    POSITIVE LOGITS
    AddTagHelper
    0.80
     deschis
    0.75
     initComponents
    0.73
     ivelany
    0.69
    basicConfig
    0.68
    LabelTagHelper
    0.67
    Примітки
    0.65
    Jereo
    0.65
    EDEFAULT
    0.63
     CURIAM
    0.62
    Activations Density 0.390%

    No Known Activations