© 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. 12-GEMMASCOPE-RES-16K
    11. 9304
    Prev
    Next
    INDEX
    Explanations

    references to specific data partitioning methods and their contributors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fromnode
    -0.61
    FunctionFlags
    -0.58
    thyst
    -0.57
    nteral
    -0.56
     Rowling
    -0.56
    therosclerosis
    -0.55
     endometriosis
    -0.54
    Pter
    -0.52
    Anja
    -0.52
     jenner
    -0.51
    POSITIVE LOGITS
     HALL
    0.55
     Hall
    0.55
    Hall
    0.53
     Harrell
    0.52
     Alfaro
    0.50
     hall
    0.50
     Vande
    0.49
    hall
    0.48
     McNeil
    0.47
     Katrina
    0.47
    Activations Density 2.406%

    No Known Activations