© 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. 21-GEMMASCOPE-RES-16K
    11. 14371
    Prev
    Next
    INDEX
    Explanations

    indicators of the beginning of a new section or topic within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.99
     cherchés
    -0.90
    ніципалі
    -0.89
    MLLoader
    -0.87
    sidemargin
    -0.83
    errHandler
    -0.83
     intptr
    -0.80
    Personendaten
    -0.78
     समीक्षक
    -0.78
     CreateTagHelper
    -0.78
    POSITIVE LOGITS
     The
    0.90
     This
    0.82
     https
    0.81
     What
    0.74
     It
    0.73
     How
    0.72
     There
    0.71
     cbd
    0.70
     ,
    0.70
    The
    0.67
    Activations Density 0.009%

    No Known Activations