© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8727
    Prev
    Next
    INDEX
    Explanations

    instances of the word "play" and its variations in the context of performing arts or entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.69
     Administrativna
    -0.63
    rrggbb
    -0.63
     autorytatywna
    -0.59
     ligiloj
    -0.58
    цезда
    -0.54
     Taktlose
    -0.54
    \{\\
    -0.54
    Cyfarwyddwr
    -0.54
     SwitchCompat
    -0.54
    POSITIVE LOGITS
     plays
    2.42
     Plays
    1.87
    Plays
    1.73
    plays
    1.61
     juega
    1.00
     spielt
    0.93
     играет
    0.85
     spelar
    0.75
     joue
    0.74
     performs
    0.72
    Activations Density 0.174%

    No Known Activations