© 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. 6071
    Prev
    Next
    INDEX
    Explanations

    discussions about the complexity and importance of life's decisions and their impacts

    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
     يتيمه
    -0.72
     AssemblyCompany
    -0.72
    protoimpl
    -0.68
    tvguidetime
    -0.65
     version
    -0.63
     ModelExpression
    -0.57
    NewUrlParser
    -0.57
    version
    -0.56
    UnknownFields
    -0.55
    ThemeOverlay
    -0.55
    POSITIVE LOGITS
     beyond
    1.83
    beyond
    1.64
     Beyond
    1.54
    Beyond
    1.52
     BEYOND
    1.43
    不仅仅
    1.35
     more
    1.34
     much
    1.31
    不止
    1.23
    มากกว่า
    1.18
    Activations Density 0.286%

    No Known Activations