© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15367
    Prev
    Next
    INDEX
    Explanations

    references to connections or linking concepts

    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
    PerformLayout
    -0.82
     ivelany
    -0.81
    GraphicsUnit
    -0.78
     nahilalakip
    -0.77
     GoogleFonts
    -0.75
    CompilerServices
    -0.74
    ğraf
    -0.74
    ambique
    -0.73
    ToBounds
    -0.71
     AssemblyCompany
    -0.71
    POSITIVE LOGITS
     dots
    0.72
     Connections
    0.71
     CONNECT
    0.68
     getConnection
    0.66
     Connecting
    0.66
    CONNECT
    0.65
    connecting
    0.64
    connections
    0.64
     conn
    0.64
     connections
    0.64
    Activations Density 0.095%

    No Known Activations