© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 9688
    Prev
    Next
    INDEX
    Explanations

    elements related to alternate arrangements and compositions in structured contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.89
    tanleria
    -0.82
    SharedDtor
    -0.82
    Personendaten
    -0.81
     kaarangay
    -0.78
     ویکی‌پدی
    -0.76
     EconPapers
    -0.76
    featureID
    -0.75
    InjectAttribute
    -0.75
     autorytatywna
    -0.73
    POSITIVE LOGITS
     الحره
    0.49
     (;;
    0.47
     bouche
    0.46
     delle
    0.46
    ّا
    0.44
     visuales
    0.43
    Tempo
    0.43
    ENDA
    0.42
    же
    0.41
    ENI
    0.41
    Activations Density 5.456%

    No Known Activations