© 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. 5-GEMMASCOPE-RES-16K
    11. 5393
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to variety and breadth of options or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.87
    Geplaatst
    -0.80
     ComVisible
    -0.78
    InputBorder
    -0.76
    FormTagHelper
    -0.76
     onCreateView
    -0.75
     vermelhas
    -0.74
    XtraReports
    -0.73
    abstractmethod
    -0.71
    ConstraintMaker
    -0.70
    POSITIVE LOGITS
     widen
    0.79
     wide
    0.78
     wider
    0.78
     breadth
    0.73
     Wider
    0.72
     possibilities
    0.69
     range
    0.69
     width
    0.69
     widest
    0.68
     broaden
    0.68
    Activations Density 0.505%

    No Known Activations