© 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. 12-GEMMASCOPE-RES-16K
    11. 508
    Prev
    Next
    INDEX
    Explanations

    quotations and dialogue within the text

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

    The neuron strongly detects opening quotation marks or the start of a quoted passage (the beginning of direct quotations).

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.93
    aarrggbb
    -0.75
     Roskov
    -0.72
     Autorizaciones
    -0.70
    MessageTagHelper
    -0.67
    __(/*!
    -0.66
    expandindo
    -0.66
     nahilalakip
    -0.66
    HideFlags
    -0.65
     '\\;'
    -0.65
    POSITIVE LOGITS
     “
    0.55
    [
    0.54
    “
    0.53
     ‘
    0.52
     often
    0.49
    "
    0.47
     [
    0.47
     "
    0.46
    ‌کنندگان
    0.46
    ’
    0.45
    Activations Density 0.182%

    No Known Activations