© 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. 15-GEMMASCOPE-RES-16K
    11. 6285
    Prev
    Next
    INDEX
    Explanations

    action words related to data handling and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plastiques
    -0.58
    esModule
    -0.57
     Sociales
    -0.55
     Cancelar
    -0.53
     prêts
    -0.52
    IsContent
    -0.48
     Vri
    -0.47
     naturelles
    -0.46
     MediatR
    -0.45
    MimeType
    -0.45
    POSITIVE LOGITS
     inserted
    0.70
     into
    0.70
    Into
    0.68
     insertion
    0.67
     insert
    0.67
     туда
    0.67
     inserting
    0.66
    Inserting
    0.63
    expandindo
    0.62
     added
    0.61
    Activations Density 0.359%

    No Known Activations