© 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. 4543
    Prev
    Next
    INDEX
    Explanations

    references to statistical analysis and parameters

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

    Comes after the word "the"

    np_acts-logits-general · gemini-2.0-flash

    explaining a reason or characteristic

    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
    قيقي
    -0.57
     vecchia
    -0.55
     principaux
    -0.54
     vrais
    -0.53
     officielles
    -0.53
    adə
    -0.51
     Lieblings
    -0.50
     irgende
    -0.49
    essentiel
    -0.48
    Reco
    -0.47
    POSITIVE LOGITS
     fact
    1.11
     lack
    1.07
     Tatsache
    0.96
     sheer
    0.95
    fact
    0.90
     extensive
    0.87
     high
    0.84
    lack
    0.83
     huge
    0.83
    huge
    0.81
    Activations Density 0.610%

    No Known Activations