© 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. 3917
    Prev
    Next
    INDEX
    Explanations

    phrases that contribute to legal argumentation and questioning the validity of evidence or decisions in judicial contexts

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

    Preceding "is" or "be" followed by a negative word

    np_acts-logits-general · gemini-2.0-flash

    without merit

    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
     otomatig
    -0.68
    Personensuche
    -0.66
     nahilalakip
    -0.65
     AssemblyCompany
    -0.64
    AndEndTag
    -0.62
     ExecuteAsync
    -0.61
    tagHelperRunner
    -0.60
    rungsseite
    -0.60
    Autoritní
    -0.59
    RenderAtEndOf
    -0.56
    POSITIVE LOGITS
     unnecessary
    1.15
     pointless
    1.15
     irrelevant
    1.14
     superfluous
    1.14
     redundant
    1.05
     useless
    1.05
     impractical
    1.01
     Irrelevant
    1.00
     moot
    0.99
     inutile
    0.97
    Activations Density 0.738%

    No Known Activations