© 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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1729
    Prev
    Next
    INDEX
    Explanations

    future-oriented statements, particularly related to actions that will be taken

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

    future actions and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     becauſe
    -0.56
     zalando
    -0.55
     risking
    -0.54
     saying
    -0.54
     dared
    -0.53
     dares
    -0.53
     Autre
    -0.53
    lında
    -0.52
     qed
    -0.52
     sayin
    -0.52
    POSITIVE LOGITS
    MemoryWarning
    0.64
    TypedDataSet
    0.64
    sizeCache
    0.60
     then
    0.57
     Normdatei
    0.54
     need
    0.54
    мати
    0.53
    จะ
    0.52
     кӀ
    0.52
    determin
    0.51
    Activations Density 0.059%

    No Known Activations