© 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. 27817
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and quotation indicators in dialogue

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

    closing quotes

    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
     للمعارف
    -0.89
    oredCriteria
    -0.86
    CloseOperation
    -0.84
    enumi
    -0.82
    RectangleBorder
    -0.81
    CPtr
    -0.81
     المعيارى
    -0.79
    脚注の使い方
    -0.79
    mybatisplus
    -0.75
    enumii
    -0.75
    POSITIVE LOGITS
     "
    0.85
     “
    0.78
     '
    0.62
    “
    0.57
     ‘
    0.56
     «
    0.56
    /*
    0.52
     "[
    0.52
     ''
    0.52
     ”
    0.50
    Activations Density 0.074%

    No Known Activations