© 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. 0-GEMMASCOPE-RES-16K
    11. 9591
    Prev
    Next
    INDEX
    Explanations

    references to memory addresses in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     z
    -0.60
     effect
    -0.56
     de
    -0.54
     Dist
    -0.53
     has
    -0.53
     &
    -0.53
     se
    -0.52
     he
    -0.51
     Fac
    -0.50
     Co
    -0.50
    POSITIVE LOGITS
     Monfieur
    0.99
     religieuses
    0.99
     étrangères
    0.93
     AssemblyProduct
    0.90
     étrangère
    0.88
     iſt
    0.87
     $_"
    0.86
    antaranya
    0.84
     Theſe
    0.84
     Anſ
    0.83
    Activations Density 0.138%

    No Known Activations