© 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. 1869
    Prev
    Next
    INDEX
    Explanations

    descriptions of places and experiences related to exploration and nature

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

    phrases describing activities and actions that can be done at tourist destinations.

    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
    BSITE
    -0.52
     nabíd
    -0.47
     '\\;'
    -0.45
    ttemberg
    -0.43
     menawarkan
    -0.43
     bezpeč
    -0.42
    Notae
    -0.41
     beleid
    -0.40
     nabí
    -0.40
     geïsole
    -0.40
    POSITIVE LOGITS
     strolled
    0.79
     stroll
    0.77
     strolling
    0.75
     walked
    0.74
     spend
    0.71
     walking
    0.69
     dine
    0.69
     walk
    0.68
     spent
    0.66
     dined
    0.62
    Activations Density 0.213%

    No Known Activations