© 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. 2341
    Prev
    Next
    INDEX
    Explanations

    occurrences of contextually significant linking phrases and references

    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
    Билгалдахарш
    -0.71
     snippetHide
    -0.66
    IonicModule
    -0.63
    
    -0.62
    رشف
    -0.61
    migrationBuilder
    -0.60
    Autoritní
    -0.57
     дописавши
    -0.56
     NSCoder
    -0.54
    MessageTagHelper
    -0.51
    POSITIVE LOGITS
     first
    4.20
    first
    3.62
    First
    2.84
     FIRST
    2.73
     first
    2.72
     primero
    2.68
     eerste
    2.68
     pertama
    2.67
     primeiro
    2.62
     primeira
    2.59
    Activations Density 1.416%

    No Known Activations