© 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. 10-GEMMASCOPE-RES-16K
    11. 4456
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and their results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sund
    -0.34
     noten
    -0.31
     sands
    -0.31
    RequestMapping
    -0.31
    canActivate
    -0.31
    ماند
    -0.31
    віть
    -0.30
     iko
    -0.29
     учащихся
    -0.29
     Eintritt
    -0.28
    POSITIVE LOGITS
     EconPapers
    0.57
    RenderAtEndOf
    0.57
    PostInfinity
    0.52
    ScopeManager
    0.51
    encodeWith
    0.51
     تكبرها
    0.51
    WithIOException
    0.51
     sebaliknya
    0.50
    RegressionTest
    0.49
    клопе
    0.48
    Activations Density 1.924%

    No Known Activations