© 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. 12632
    Prev
    Next
    INDEX
    Explanations

    recreational and entertainment-related activities and amenities

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

    nouns related to specific places, structures, or facilities (like entertainment venues, buildings, rooms, and infrastructure).

    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
     plegable
    -0.40
     Infór
    -0.40
     Administrativna
    -0.39
     administrativos
    -0.36
     мәкал
    -0.36
     Rechnung
    -0.35
     hidrá
    -0.34
     morado
    -0.33
     içi
    -0.33
    內的
    -0.33
    POSITIVE LOGITS
     rooms
    0.81
     room
    0.79
     tower
    0.74
     station
    0.73
     hall
    0.73
     centre
    0.73
     zone
    0.73
     area
    0.73
     center
    0.72
     queſta
    0.69
    Activations Density 0.516%

    No Known Activations