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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1516
    Prev
    Next
    INDEX
    Explanations

    HTML or markup language entities and formatting tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StatelessWidget
    -0.51
     EconPapers
    -0.47
    endregion
    -0.44
     Contreras
    -0.43
    ControllerTest
    -0.41
    MMdd
    -0.41
     XCTest
    -0.41
    SQLException
    -0.41
    ésultat
    -0.40
    ↺
    -0.39
    POSITIVE LOGITS
    nbsp
    0.69
    > 
    0.56
    pecto
    0.53
    quad
    0.52
    ftagPool
    0.51
    )\,
    0.50
    ########.
    0.50
     autorytatywna
    0.50
    mspace
    0.50
     
    0.50
    Activations Density 0.936%

    No Known Activations