© 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. 4133
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that signal the end of thoughts or sentences

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

    Followed by “but”

    np_acts-logits-general · gemini-2.0-flash

    but introducing contrast

    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
     CreateTagHelper
    -0.69
    bootstrapcdn
    -0.68
    Autoritní
    -0.66
     betweenstory
    -0.65
    styleType
    -0.53
    BorderFactory
    -0.52
     ویکی‌پدیا
    -0.52
    Kjelder
    -0.50
    carpa
    -0.50
    ImageContext
    -0.49
    POSITIVE LOGITS
     but
    3.20
     But
    2.59
    But
    2.52
    but
    2.49
     pero
    2.41
     nhưng
    2.40
     BUT
    2.36
     tetapi
    2.33
     entanto
    2.30
     namun
    2.29
    Activations Density 0.562%

    No Known Activations