© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13208
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to source control and version management in software development

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

    words that are part of technical or software development documentation and discussions.

    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
    glVertex
    -0.47
    featureID
    -0.46
    WebServlet
    -0.45
    writeField
    -0.45
     PyLong
    -0.44
    createClass
    -0.44
     CURLOPT
    -0.43
    UnitTesting
    -0.43
    ̈́
    -0.43
    IBOutlet
    -0.41
    POSITIVE LOGITS
     software
    1.27
     softwares
    1.13
     tools
    1.13
     tool
    1.10
     platforms
    0.99
    工具
    0.99
    software
    0.97
     logiciels
    0.94
     herramienta
    0.90
    软件
    0.89
    Activations Density 1.111%

    No Known Activations