© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13486
    Prev
    Next
    INDEX
    Explanations

    terms related to Tibetan geographical names and their meanings

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

    geographic locations and elevation measurements on the Tibetan Plateau.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Exactos
    -0.57
     OMITBAD
    -0.56
    تقاوى
    -0.56
    httphttps
    -0.56
    astify
    -0.53
    XmlEnum
    -0.52
     nahilalakip
    -0.50
    InputBorder
    -0.49
    verwijspagina
    -0.47
     VizieR
    -0.45
    POSITIVE LOGITS
     Tibetan
    0.87
     Tibet
    0.82
     Bhutan
    0.70
     tibet
    0.70
    Tib
    0.63
     Lama
    0.60
     Ladakh
    0.59
     Dalai
    0.57
     Himalayan
    0.55
     Sikkim
    0.53
    Activations Density 0.076%

    No Known Activations