© 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. 9633
    Prev
    Next
    INDEX
    Explanations

    programming constructs that indicate conditional logic and response handling

    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
    Tembelea
    -0.78
     насељу
    -0.74
     purpoſe
    -0.72
     مشين
    -0.71
     betweenstory
    -0.70
     esternos
    -0.68
    UnusedPrivate
    -0.67
     Monfieur
    -0.66
     חיצוניים
    -0.65
    SharedCtor
    -0.65
    POSITIVE LOGITS
    JButton
    0.59
    velas
    0.51
     BoxDecoration
    0.51
    ="@+
    0.51
     Neural
    0.50
    tiba
    0.49
     neural
    0.49
     jButton
    0.49
    ourdes
    0.48
    ILayout
    0.47
    Activations Density 0.105%

    No Known Activations