© 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. 15490
    Prev
    Next
    INDEX
    Explanations

    references to model classes and data structures in programming context

    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
     Efq
    -1.41
     purpoſe
    -1.22
     themſelves
    -1.18
     pleaſure
    -1.17
     myſelf
    -1.17
     poffible
    -1.16
     Shakspeare
    -1.14
     himſelf
    -1.12
     Jefus
    -1.12
     itſelf
    -1.10
    POSITIVE LOGITS
    model
    1.51
    Model
    1.19
     Model
    0.99
    MODEL
    0.85
    Models
    0.82
    models
    0.81
    TableModel
    0.80
     model
    0.78
     MODEL
    0.72
    ItemModel
    0.59
    Activations Density 0.129%

    No Known Activations