© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 37643
    Prev
    Next
    INDEX
    Explanations

    phrases related to social impact and humanitarian issues

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

    numbers and quantities

    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
     kasarigan
    -0.49
    ModelSerializer
    -0.46
    awtextra
    -0.44
    setViewportView
    -0.40
    diyah
    -0.37
    новништво
    -0.37
    неопр
    -0.36
     contextLoads
    -0.36
     ligiloj
    -0.35
    AndroidJUnit
    -0.35
    POSITIVE LOGITS
     thousands
    2.28
     countless
    2.16
     hundreds
    2.14
    thousands
    2.06
    Thousands
    2.00
     Thousands
    1.98
    hundreds
    1.93
     millions
    1.91
    Hundreds
    1.88
     Hundreds
    1.86
    Activations Density 0.128%

    No Known Activations