© 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. 9165
    Prev
    Next
    INDEX
    Explanations

    words related to cause and effect relationships in scientific 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
    WebVitals
    -0.97
    IntoConstraints
    -0.86
     ExecuteAsync
    -0.78
    SharedCtor
    -0.78
    DoubleQuotes
    -0.76
    脚注の使い方
    -0.75
    Portale
    -0.75
    Parcelize
    -0.74
    ViewFeatures
    -0.73
     unmute
    -0.71
    POSITIVE LOGITS
     resulted
    1.56
     resulting
    1.53
    resulting
    1.27
     resultant
    0.98
     caused
    0.93
     résult
    0.87
     resultar
    0.82
     arising
    0.80
    caused
    0.74
     due
    0.73
    Activations Density 0.134%

    No Known Activations