© 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. 14934
    Prev
    Next
    INDEX
    Explanations

    references to comparisons or contrasts between different groups or individuals

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

    after capitalized words/names

    np_acts-logits-general · gemini-2.0-flash

    negative informal criticism

    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
     ciasc
    -0.80
     våre
    -0.68
     habet
    -0.66
     quæ
    -0.65
     citoy
    -0.65
     AssemblyTitle
    -0.64
     yder
    -0.63
     généralement
    -0.61
     quelquefois
    -0.61
     plufieurs
    -0.61
    POSITIVE LOGITS
     stuff
    1.13
     stupid
    1.10
     thing
    1.09
     damn
    0.89
     crappy
    0.89
    stupid
    0.87
     thingy
    0.87
     crap
    0.87
     damned
    0.85
     shitty
    0.85
    Activations Density 0.579%

    No Known Activations