Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8539
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to curfews and restrictions

    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
     Waray
    -0.61
     acceptor
    -0.54
     rifi
    -0.49
    ₦
    -0.48
    Portale
    -0.47
     aceptar
    -0.46
     paulista
    -0.46
     ajutor
    -0.44
    Lagos
    -0.44
    yacht
    -0.44
    POSITIVE LOGITS
     Kashmir
    0.93
    Kash
    0.83
    enderror
    0.81
     Srinagar
    0.80
     Jammu
    0.78
    Srin
    0.77
     propOrder
    0.77
    aarrggbb
    0.72
    elemField
    0.69
    LabelTagHelper
    0.68
    Activations Density 0.035%

    No Known Activations