© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 11080
    Prev
    Next
    INDEX
    Explanations

    elements and concepts related to scientific methods and experimental results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Weldon
    -0.61
     saites
    -0.49
     rând
    -0.43
    ModelBuilder
    -0.43
     XCTest
    -0.42
    ghis
    -0.42
     Langdon
    -0.42
    دانشنامهٔ
    -0.42
     Chwiliwch
    -0.42
     Edison
    -0.41
    POSITIVE LOGITS
     asterisk
    0.93
    ******
    0.92
     aster
    0.89
    ****
    0.86
    **
    0.85
    (**
    0.83
    *****
    0.83
     ******
    0.83
    ***
    0.81
    $*
    0.81
    Activations Density 1.983%

    No Known Activations