© 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. 18-GEMMASCOPE-RES-16K
    11. 4127
    Prev
    Next
    INDEX
    Explanations

    punctuation, specifically commas and periods

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

    Followed by a comma and then "but"

    np_acts-logits-general · gemini-2.0-flash

    punctuation followed by connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -0.77
     when
    -0.73
     for
    -0.67
     before
    -0.67
    <bos>
    -0.60
     by
    -0.60
     until
    -0.59
     to
    -0.56
     during
    -0.55
     that
    -0.55
    POSITIVE LOGITS
     كومونز
    1.00
    principalColumn
    1.00
    URLException
    0.97
     تانيه
    0.91
    ChildScrollView
    0.86
     MainAxisSize
    0.84
    存于互联网档案馆
    0.83
     Мексичка
    0.82
     محفوظة
    0.81
    /**
    0.80
    Activations Density 0.554%

    No Known Activations