© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27807
    Prev
    Next
    INDEX
    Explanations

    phrases related to formal acceptance processes or guidelines

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

    explicitly, directly, personally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     specifically
    -0.82
     специально
    -0.75
     purposely
    -0.73
    officially
    -0.73
     Specifically
    -0.73
     explicitly
    -0.72
     officially
    -0.72
     CreateTagHelper
    -0.71
    Specifically
    -0.71
    specifically
    -0.71
    POSITIVE LOGITS
     genomen
    0.54
     kohta
    0.50
    orship
    0.49
    ঃ
    0.49
    ว่า
    0.47
    unehmen
    0.47
     umgekehrt
    0.47
     ว่า
    0.47
     ligiloj
    0.47
     foon
    0.45
    Activations Density 0.464%

    No Known Activations