© 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-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6820
    Prev
    Next
    INDEX
    Explanations

    references to nodes and their associated properties in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 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
    s
    -0.42
    Gesam
    -0.38
     Gesam
    -0.38
     American
    -0.37
    ../../
    -0.36
     Dür
    -0.36
     the
    -0.35
    7
    -0.35
     TOTAL
    -0.35
     total
    -0.35
    POSITIVE LOGITS
     node
    1.20
     Node
    1.20
     getNode
    1.13
     Nodes
    1.11
    Node
    1.10
     NODE
    1.07
     nodes
    1.02
    getNode
    0.99
    tonode
    0.96
    addNode
    0.94
    Activations Density 0.107%

    No Known Activations