© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27239
    Prev
    Next
    INDEX
    Explanations

    terminology related to graph theory

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

    graph nodes and edges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unhofer
    -0.52
     cro
    -0.46
    awaiter
    -0.46
     podio
    -0.45
    setPosition
    -0.44
     mid
    -0.44
    ピ
    -0.43
    Cro
    -0.43
    cro
    -0.42
    ChildScrollView
    -0.42
    POSITIVE LOGITS
     vertices
    0.75
     nodes
    0.73
     Nodes
    0.73
     adjacency
    0.73
     subgraph
    0.72
     Connectivity
    0.71
    jacency
    0.69
    Vertices
    0.69
    fromnode
    0.68
     getNode
    0.68
    Activations Density 1.243%

    No Known Activations