© 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. 20-GEMMASCOPE-RES-16K
    11. 15122
    Prev
    Next
    INDEX
    Explanations

    negations and qualifiers related to suitability, effectiveness, or performance

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

    Followed by adverbs of certainty or degree

    np_acts-logits-general · gemini-2.0-flash

    not necessarily

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.59
     nonetheless
    -0.56
     سكانية
    -0.55
     Paglinawan
    -0.53
    almost
    -0.51
    MessageTagHelper
    -0.51
     хоть
    -0.50
     tartalomajánló
    -0.50
    curious
    -0.48
    先是
    -0.48
    POSITIVE LOGITS
     necessarily
    1.38
     exactly
    1.26
     quite
    1.20
     fully
    1.19
     entirely
    1.19
     necessariamente
    1.17
     sepenuhnya
    1.13
     exatamente
    1.10
     necesariamente
    1.09
     completely
    1.08
    Activations Density 0.830%

    No Known Activations