© 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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14506
    Prev
    Next
    INDEX
    Explanations

    instances of the word "play" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.85
    EDEFAULT
    -0.82
    contentLoaded
    -0.81
    gnore
    -0.79
    featureID
    -0.79
    EndContext
    -0.77
     nakalista
    -0.73
    
    -0.73
    NamedQueries
    -0.68
    XmlAccessorType
    -0.67
    POSITIVE LOGITS
    wrights
    0.71
     PLAY
    0.64
    PLAY
    0.63
     games
    0.63
     play
    0.62
    doh
    0.58
    wright
    0.57
     plays
    0.56
    fulness
    0.56
     Play
    0.56
    Activations Density 0.071%

    No Known Activations