© 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. 3-GEMMASCOPE-RES-16K
    11. 7528
    Prev
    Next
    INDEX
    Explanations

    actions related to the removal of elements or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initView
    -0.58
     courseId
    -0.56
     dataType
    -0.53
    GenerationType
    -0.52
    ArgumentParser
    -0.52
     psz
    -0.52
    Jîn
    -0.51
    CellStyle
    -0.51
     getLayout
    -0.50
     orderId
    -0.50
    POSITIVE LOGITS
    remove
    3.42
     remove
    3.38
     Remove
    3.14
    Remove
    3.11
     removal
    2.83
     removing
    2.70
     removed
    2.67
     REMOVE
    2.67
     removes
    2.67
     Removal
    2.61
    Activations Density 0.093%

    No Known Activations