© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 7860
    Prev
    Next
    INDEX
    Explanations

    elements related to structured data representations, particularly in a programming or mathematical context

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

    Edges and nodes in diagrams

    np_acts-logits-general · gemini-2.0-flash

    edge labels and styles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.65
     يتيمه
    -0.64
    ScopeManager
    -0.62
    RenderAtEndOf
    -0.61
    TestingModule
    -0.56
    UrlResolution
    -0.55
    
    -0.55
    ArgsConstructor
    -0.55
    SequentialGroup
    -0.50
    AccessorTable
    -0.50
    POSITIVE LOGITS
     Nodes
    0.61
     nodes
    0.58
    Nodes
    0.49
     node
    0.47
    nodes
    0.45
     Node
    0.45
    tonode
    0.45
     drag
    0.45
    节点
    0.42
     Arrow
    0.42
    Activations Density 0.581%

    No Known Activations