© 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. 22-GEMMASCOPE-RES-16K
    11. 15128
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Linked lists and node structures

    np_acts-logits-general · gemini-2.0-flash

    list node operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.63
    IsContent
    -0.63
    encodeWith
    -0.57
     Sauer
    -0.53
     OnInit
    -0.51
    XmlAccessType
    -0.50
    IDO
    -0.50
    UIControlState
    -0.49
    ///</
    -0.49
     AssemblyTitle
    -0.49
    POSITIVE LOGITS
    ListNode
    0.87
     node
    0.85
     head
    0.84
     ListNode
    0.81
    node
    0.79
     Node
    0.78
    Node
    0.77
    head
    0.76
     nodes
    0.76
     nodo
    0.75
    Activations Density 0.136%

    No Known Activations