© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 8522
    Prev
    Next
    INDEX
    Explanations

    instances of the word "play" and its variations, indicating a focus on actions or narratives related to performance and roles

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

    the word "play" or "playing"

    np_acts-logits-general · gemini-2.0-flash

    playing roles or games

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.61
    KommentareTeilen
    -0.60
    onsored
    -0.60
    XmlAccessorType
    -0.57
    astify
    -0.56
     volando
    -0.56
    fromCharCode
    -0.56
    Földrajzportál
    -0.54
    kozá
    -0.53
     dotyczące
    -0.52
    POSITIVE LOGITS
     games
    0.83
     golf
    0.69
     host
    0.69
     favorites
    0.66
     coy
    0.66
     ball
    0.66
     catch
    0.64
     havoc
    0.62
     poss
    0.62
     tru
    0.62
    Activations Density 0.079%

    No Known Activations