© 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. 16370
    Prev
    Next
    INDEX
    Explanations

    questions and issues related to common methods and parameters in programming or legal contexts

    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
    SourceChecksum
    -0.58
    Brainz
    -0.55
    RenderAtEndOf
    -0.55
     Paglinawan
    -0.54
    
    -0.54
    atouille
    -0.50
     springfox
    -0.49
    ecord
    -0.49
    település
    -0.48
    ocardial
    -0.48
    POSITIVE LOGITS
     preexisting
    0.89
     Existing
    0.79
    writeFieldEnd
    0.77
     sẵn
    0.75
     existing
    0.75
    もともと
    0.73
    Existing
    0.72
     '\\;'
    0.71
    existing
    0.69
    already
    0.69
    Activations Density 0.218%

    No Known Activations