© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 16135
    Prev
    Next
    INDEX
    Explanations

    structured data and categorical characteristics in research or clinical studies

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

    money, numbers, code, and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     betweenstory
    -1.15
    principalColumn
    -1.00
     esternos
    -0.98
     noDo
    -0.96
    AndEndTag
    -0.95
    rawDesc
    -0.94
     kaarangay
    -0.93
    ंदीखरीदारी
    -0.93
    migrationBuilder
    -0.92
    RegressionTest
    -0.91
    POSITIVE LOGITS
    <eos>
    0.39
     litté
    0.31
                                   
    0.30
                             
    0.30
    ↵↵
    0.29
    ing
    0.29
    Và
    0.28
                            
    0.28
                     
    0.27
                         
    0.27
    Activations Density 0.029%

    No Known Activations