© 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. 16-GEMMASCOPE-RES-16K
    11. 5788
    Prev
    Next
    INDEX
    Explanations

    negations and comparative phrases indicating contrast

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

    "not" followed by a negative concept

    np_acts-logits-general · gemini-2.0-flash

    not or rather than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NgModule
    -0.53
     dourada
    -0.48
    achau
    -0.48
    L
    -0.45
    B
    -0.43
     Legendre
    -0.43
    UrlResolution
    -0.43
    A
    -0.42
     feminina
    -0.41
    不等
    -0.41
    POSITIVE LOGITS
     necessarily
    1.00
     merely
    0.93
     مشين
    0.92
     necesariamente
    0.91
     just
    0.90
    necessarily
    0.89
    NameInMap
    0.89
    жели
    0.88
     дописавши
    0.86
    それとも
    0.85
    Activations Density 0.215%

    No Known Activations