© 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. 8898
    Prev
    Next
    INDEX
    Explanations

    patterns related to assembly language and compiler instructions

    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
     comparison
    -1.29
     comparing
    -1.25
     compare
    -1.22
     comparisons
    -1.21
    Compare
    -1.19
     compares
    -1.18
     comparaison
    -1.18
     Comparison
    -1.17
     Compare
    -1.15
    compare
    -1.13
    POSITIVE LOGITS
    makeConstraints
    0.58
    strSql
    0.55
    XPATH
    0.52
     bege
    0.44
     expression
    0.43
    риев
    0.43
    expression
    0.43
    ,))
    0.42
     gql
    0.42
     CURIAM
    0.42
    Activations Density 0.418%

    No Known Activations