© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 11417
    Prev
    Next
    INDEX
    Explanations

    connective phrases and references to actions related to decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ddelweddau
    -0.69
    serviceWorker
    -0.59
    protoc
    -0.56
    zta
    -0.52
     surla
    -0.52
     Wilde
    -0.50
     меры
    -0.49
    āla
    -0.48
    står
    -0.48
    èze
    -0.48
    POSITIVE LOGITS
     CreateTagHelper
    0.88
    TypedDataSet
    0.71
    chaun
    0.62
     незавершена
    0.61
     randomly
    0.58
    庁
    0.58
    Pfalz
    0.57
     فريبيس
    0.57
     beginnetje
    0.56
     lalu
    0.56
    Activations Density 0.536%

    No Known Activations