© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 11288
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to programming and APIs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical documentation and code repositories with links, setup instructions, and metadata.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.51
    SharedDtor
    -0.50
    TestingModule
    -0.45
    MigrationBuilder
    -0.43
     kasarigan
    -0.43
    RegressionTest
    -0.43
    GEBURTS
    -0.42
     跳转至
    -0.40
    regel
    -0.40
    /*---
    -0.39
    POSITIVE LOGITS
     demo
    0.82
     demos
    0.68
     github
    0.67
     Demo
    0.66
     demonstration
    0.65
    Demo
    0.64
    demo
    0.63
     DEMO
    0.61
     inspired
    0.61
     démo
    0.59
    Activations Density 0.914%

    No Known Activations