© 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. 2-GEMMASCOPE-RES-16K
    11. 2251
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate dependence or relationships among factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propTypes
    -0.47
     exig
    -0.45
     Consist
    -0.45
     sprays
    -0.45
     caches
    -0.44
    lblNewLabel
    -0.44
     chats
    -0.43
    exist
    -0.43
     Exist
    -0.43
     ducks
    -0.43
    POSITIVE LOGITS
     occurs
    1.32
     depends
    1.26
     consists
    1.22
     exists
    1.18
     belongs
    1.17
    volves
    1.13
     involves
    1.09
     happens
    1.09
     varies
    1.09
     requires
    1.05
    Activations Density 0.237%

    No Known Activations