© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103975
    Prev
    Next
    INDEX
    Explanations

    directions and positions within spatial or geographic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.57
    новниш
    -0.55
     للمعارف
    -0.49
     simplifié
    -0.49
     cologne
    -0.48
    ⤹
    -0.47
    balleur
    -0.45
    logna
    -0.44
     Piles
    -0.44
     conges
    -0.44
    POSITIVE LOGITS
     downward
    0.56
     Hauteur
    0.56
     height
    0.52
     getHeight
    0.52
     downwards
    0.52
     upward
    0.51
     hauteur
    0.50
     elevation
    0.49
     altura
    0.48
    height
    0.48
    Activations Density 0.096%

    No Known Activations