© 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. 111365
    Prev
    Next
    INDEX
    Explanations

    terms related to ergonomic design and ergonomics

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

    ergonomics or ergative linguistics

    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
    boxylic
    -0.41
     Exc
    -0.40
    Exc
    -0.39
     cier
    -0.36
    getFile
    -0.36
     pid
    -0.35
    astify
    -0.35
     exc
    -0.34
     Fä
    -0.33
     frosts
    -0.33
    POSITIVE LOGITS
     ergonomics
    0.73
     ergonomic
    0.73
     Ergonomic
    0.65
     diseño
    0.61
     ergonom
    0.61
    AndEndTag
    0.59
    Erg
    0.57
     Erg
    0.56
     design
    0.56
     diseños
    0.55
    Activations Density 0.006%

    No Known Activations