© 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-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 10677
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to abstract syntax trees (AST) in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nere
    -0.47
    nerv
    -0.47
     Neur
    -0.45
    basket
    -0.43
    arme
    -0.42
    Nc
    -0.42
     Natives
    -0.42
    Nav
    -0.40
     Neutral
    -0.39
     Nerv
    -0.39
    POSITIVE LOGITS
     node
    2.44
    node
    1.98
     Node
    1.49
    Node
    1.46
     nodes
    1.17
     NODE
    1.16
    节点
    1.13
    NODE
    1.09
     nodo
    0.94
     getNode
    0.87
    Activations Density 0.240%

    No Known Activations