© 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. 9986
    Prev
    Next
    INDEX
    Explanations

    instructions related to navigation and directions

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

    phrases and vocabulary related to navigation, GPS, directions, and finding routes.

    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
    expandindo
    -0.52
    +#+
    -0.51
    
    -0.50
    出版年
    -0.50
    StructEnd
    -0.48
    protoimpl
    -0.45
     sequelize
    -0.45
     createState
    -0.44
    PostInfinity
    -0.44
     חיצוניים
    -0.42
    POSITIVE LOGITS
     directions
    1.55
     navigation
    1.54
     GPS
    1.44
     Directions
    1.35
     Navigation
    1.34
     navig
    1.34
     navigational
    1.32
     maps
    1.29
    directions
    1.27
    Directions
    1.26
    Activations Density 0.193%

    No Known Activations