© 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. 8954
    Prev
    Next
    INDEX
    Explanations

    references to user-related entities and operations

    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
    CopyWith
    -0.77
     ProductService
    -0.68
    ITT
    -0.66
    detectChanges
    -0.66
    Mald
    -0.66
    zitter
    -0.66
     ApiService
    -0.66
    itt
    -0.66
     Ples
    -0.66
     lenker
    -0.65
    POSITIVE LOGITS
    User
    2.05
     User
    1.55
     USER
    0.79
    NewUser
    0.78
    idUser
    0.75
    USER
    0.74
    ToUser
    0.74
    addUser
    0.73
    UserContext
    0.73
     IUser
    0.70
    Activations Density 0.058%

    No Known Activations