© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 10560
    Prev
    Next
    INDEX
    Explanations

    instances of gatherings or assemblies of people

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

    large groups of people assembling or gathering together.

    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
     jegy
    -0.35
     thermique
    -0.35
    eraard
    -0.34
     patrulla
    -0.34
     helft
    -0.31
     estri
    -0.30
    argento
    -0.29
    ndice
    -0.29
     abstrait
    -0.28
     juicio
    -0.28
    POSITIVE LOGITS
     gathered
    2.19
     gathering
    2.17
     gather
    2.14
     gathers
    1.99
     Gather
    1.93
     Gathering
    1.87
     assemble
    1.85
    gathering
    1.85
     assembled
    1.84
    Gathering
    1.83
    Activations Density 0.289%

    No Known Activations