© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 9019
    Prev
    Next
    INDEX
    Explanations

    references to data sources and their associated rates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.68
     opar
    -0.57
    Extinguishing
    -0.56
    ご
    -0.56
    Lou
    -0.53
     roble
    -0.52
     dok
    -0.52
     Lonely
    -0.50
     schi
    -0.50
     Morpho
    -0.50
    POSITIVE LOGITS
    AddTagHelper
    0.87
    katapos
    0.69
    rates
    0.68
    ConstraintMaker
    0.67
    etheless
    0.66
    DataSource
    0.65
     officiellement
    0.64
    ppure
    0.63
    MediaStore
    0.62
     kaynağından
    0.62
    Activations Density 0.081%

    No Known Activations