© 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. 4-GEMMASCOPE-RES-16K
    11. 12984
    Prev
    Next
    INDEX
    Explanations

    references to numerical values or codes in a structured format

    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
    hypothesis
    -0.56
    uté
    -0.56
     müßte
    -0.52
     Runway
    -0.52
     Moscou
    -0.51
     operativo
    -0.51
     urbanos
    -0.51
    amarin
    -0.51
    ynka
    -0.50
    Hypothesis
    -0.50
    POSITIVE LOGITS
    SourceChecksum
    0.79
    InteropServices
    0.73
     Савезне
    0.71
    principalTable
    0.70
     cherchés
    0.70
     متعلقه
    0.68
     Италијани
    0.67
    تقاوى
    0.64
     initComponents
    0.63
     nonUne
    0.62
    Activations Density 1.785%

    No Known Activations