© 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 - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 5462
    Prev
    Next
    INDEX
    Explanations

    instances of the term "Kunming" and related references, especially in a scientific or medical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hahn
    -0.69
     Benson
    -0.69
    이블
    -0.68
    🔥🔥
    -0.67
     Boas
    -0.63
    Benson
    -0.62
     рас
    -0.62
     Jad
    -0.61
    ()+"
    -0.60
    Johannes
    -0.60
    POSITIVE LOGITS
     ApiException
    0.94
     Flamingo
    0.90
     rospy
    0.83
     autorytatywna
    0.83
     getActivity
    0.82
    ViewFeatures
    0.81
    onAttach
    0.81
    __':
    0.81
     tearDown
    0.80
    Strut
    0.80
    Activations Density 0.918%

    No Known Activations