© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 12267
    Prev
    Next
    INDEX
    Explanations

    cohesive and connecting words or phrases that enhance the flow of a narrative or description

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

    land and sea and air

    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
     دم
    -0.31
    Fluid
    -0.29
    spiller
    -0.28
    drawSprites
    -0.28
     geslacht
    -0.28
    liquid
    -0.28
    flüs
    -0.27
    Sain
    -0.27
    pNext
    -0.27
     demo
    -0.27
    POSITIVE LOGITS
     inland
    1.16
     terrestrial
    0.97
     ashore
    0.91
     onshore
    0.90
     upland
    0.84
     terrestres
    0.81
     uplands
    0.81
     Terrestrial
    0.80
     dry
    0.78
     mountains
    0.77
    Activations Density 0.039%

    No Known Activations