© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-GEMMASCOPE-RES-16K
    11. 5083
    Prev
    Next
    INDEX
    Explanations

    phrases and forms related to the concept of completion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XtraBars
    -0.73
    zzard
    -0.72
    JRadioButton
    -0.71
    ագրություններ
    -0.70
    sidemargin
    -0.69
     MatDialog
    -0.66
    spyOn
    -0.65
     JsonResult
    -0.64
    Berger
    -0.63
    fontsize
    -0.63
    POSITIVE LOGITS
     Comple
    1.50
     complete
    1.42
     completed
    1.41
    Complete
    1.41
    COMPLETE
    1.39
    complete
    1.36
     comple
    1.35
     Complete
    1.35
     COMPLETE
    1.34
    completed
    1.32
    Activations Density 0.065%

    No Known Activations