© 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. 14592
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and certain formatting elements, indicating a focus on text structure or syntax

    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
     over
    -0.50
    ServiceException
    -0.49
     full
    -0.48
     co
    -0.48
    respectively
    -0.47
     Inc
    -0.47
     respectively
    -0.47
     S
    -0.44
     B
    -0.43
     
    -0.43
    POSITIVE LOGITS
    IntoConstraints
    1.20
    TagMode
    1.13
     typelib
    0.91
    WriteTagHelper
    0.83
    DockStyle
    0.82
    ContentAsync
    0.81
    rungsseite
    0.81
    Personendaten
    0.81
     eventdata
    0.79
    EndGlobalSection
    0.79
    Activations Density 0.146%

    No Known Activations