© 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. 37-GEMMASCOPE-RES-16K
    11. 6719
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax elements and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContentAlignment
    -0.47
    glGen
    -0.45
     AppBundle
    -0.41
    ToAdd
    -0.40
    を増
    -0.40
    OrCreate
    -0.39
     AssemblyVersion
    -0.39
    aroo
    -0.39
     Za
    -0.38
    LabelTagHelper
    -0.38
    POSITIVE LOGITS
     destroy
    1.08
     cleanup
    1.06
     teardown
    1.01
     shutdown
    0.99
     Cleanup
    0.97
    destroy
    0.96
     dismantling
    0.96
     dismantle
    0.96
    cleanup
    0.92
     tearDown
    0.92
    Activations Density 0.549%

    No Known Activations