© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8849
    Prev
    Next
    INDEX
    Explanations

    references to nodes within a data structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SuppressLint
    -0.64
    ViewImports
    -0.62
     élevées
    -0.60
     aveug
    -0.59
     کنی
    -0.58
     russes
    -0.57
    ิลปะ
    -0.57
     attirer
    -0.57
     Pary
    -0.57
     kterou
    -0.57
    POSITIVE LOGITS
     node
    1.41
    node
    1.29
     nodes
    1.14
     Node
    1.06
    Node
    1.00
    nodes
    0.91
     hub
    0.89
     Nodes
    0.89
    NODE
    0.89
     NODE
    0.88
    Activations Density 0.093%

    No Known Activations