© 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. 3-GEMMASCOPE-RES-16K
    11. 9635
    Prev
    Next
    INDEX
    Explanations

    phrases focusing on the concept of obligations or payments related to various subjects

    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
     שוליים
    -0.57
    comings
    -0.55
     Egli
    -0.53
    JsonInclude
    -0.53
     CreateTagHelper
    -0.53
     >=",
    -0.53
     חיצוניים
    -0.53
    }{*}{}
    -0.52
    غرب
    -0.52
     beginnetje
    -0.51
    POSITIVE LOGITS
    انيف
    0.63
     buying
    0.62
    ContentAsync
    0.62
     purchase
    0.60
    Preço
    0.60
    Цены
    0.59
     expensive
    0.59
    gulier
    0.58
     famine
    0.58
    SequentialGroup
    0.58
    Activations Density 0.162%

    No Known Activations