© 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. 10605
    Prev
    Next
    INDEX
    Explanations

    specific syntax and structure associated with programming languages

    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
    setVerticalGroup
    -0.66
    terase
    -0.65
    ГЛА
    -0.57
     Roskov
    -0.56
    potranspiration
    -0.56
    SerializedSize
    -0.55
    AccessorTable
    -0.54
    réhen
    -0.53
    setViewportView
    -0.53
     baum
    -0.52
    POSITIVE LOGITS
    ########.
    0.60
     amitié
    0.58
     jScrollPane
    0.57
    يكب
    0.53
     representación
    0.52
    hånd
    0.51
    ulx
    0.49
     exogenous
    0.49
    addPreferredGap
    0.47
     hurtig
    0.47
    Activations Density 0.792%

    No Known Activations