© 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. 88729
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols, indicating it may be focused on formatting in text

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

    numbers or starting explanations

    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
    
    -0.92
    AddTagHelper
    -0.81
    脚注の使い方
    -0.75
     propOrder
    -0.75
    parsedMessage
    -0.75
     pinulongan
    -0.74
    RenderAtEndOf
    -0.70
    istoitu
    -0.68
    addContainerGap
    -0.66
     Normdatei
    -0.66
    POSITIVE LOGITS
    Introduction
    0.56
     Introduction
    0.52
    What
    0.49
    Explain
    0.49
    Define
    0.49
     describe
    0.48
     introduction
    0.47
    Describe
    0.47
     introduce
    0.46
     Explain
    0.46
    Activations Density 0.139%

    No Known Activations