© 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. 3037
    Prev
    Next
    INDEX
    Explanations

    expressions indicating degree or emphasis

    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
     culturelles
    -0.75
     Kearney
    -0.75
     Flanagan
    -0.74
     layer
    -0.72
    بوابة
    -0.71
     Berna
    -0.71
    newnode
    -0.70
    genas
    -0.70
    Hrsg
    -0.69
     Dooley
    -0.68
    POSITIVE LOGITS
    quite
    1.68
     quite
    1.64
     Quite
    1.51
    Quite
    1.50
     uite
    1.06
     ganske
    0.82
     تضيفلها
    0.80
     PLWABN
    0.80
    CodedInputStream
    0.79
     palettes
    0.75
    Activations Density 0.049%

    No Known Activations