© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 12795
    Prev
    Next
    INDEX
    Explanations

    instances of the word "seen" and variations of it to refer to experiences or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.87
     doInBackground
    -0.87
    principalTable
    -0.83
    
    -0.83
    webElementXpaths
    -0.81
    GEBURTSDATUM
    -0.80
    ngrx
    -0.72
    AddTagHelper
    -0.71
    IsContent
    -0.69
    MigrationBuilder
    -0.69
    POSITIVE LOGITS
    有过
    0.88
     times
    0.71
     several
    0.67
     many
    0.67
     often
    0.66
     pernah
    0.66
    做过
    0.65
     occasionally
    0.63
     कभी
    0.62
     sometimes
    0.62
    Activations Density 0.228%

    No Known Activations