© 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. 2-GEMMASCOPE-RES-16K
    11. 15510
    Prev
    Next
    INDEX
    Explanations

    references to selection processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mited
    -0.61
     avancé
    -0.60
    initComponents
    -0.59
    SharedCtor
    -0.59
     préciser
    -0.58
     conclure
    -0.57
    стракт
    -0.57
    ultad
    -0.57
     consulter
    -0.55
     apprécier
    -0.55
    POSITIVE LOGITS
     selection
    3.05
     Selection
    2.87
    Selection
    2.81
    selection
    2.81
     SELECTION
    2.47
    SELECTION
    2.37
     selections
    2.14
     Selections
    2.05
    selections
    1.83
     Auswahl
    1.78
    Activations Density 0.103%

    No Known Activations