© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 14305
    Prev
    Next
    INDEX
    Explanations

    elements related to architectural and structural design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ALE
    -0.42
    zarchiwizowane
    -0.40
    Document
    -0.40
    enerated
    -0.38
     strconv
    -0.38
     QLabel
    -0.37
    awaiter
    -0.37
    cane
    -0.37
     constant
    -0.37
     interest
    -0.37
    POSITIVE LOGITS
     layout
    0.84
     LAYOUT
    0.67
    布局
    0.66
     Layout
    0.66
     arrangement
    0.65
     topology
    0.64
     structure
    0.62
     layouts
    0.62
    STRUCTURE
    0.60
     Estructura
    0.59
    Activations Density 0.953%

    No Known Activations