© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 3200
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to recreational travel and leisure facilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.83
     IndexPath
    -0.69
    Referanser
    -0.67
     незавершена
    -0.65
     iprot
    -0.62
    URIS
    -0.61
    lone
    -0.60
     Gambit
    -0.60
    phrine
    -0.60
     uska
    -0.60
    POSITIVE LOGITS
     resort
    1.39
     Resort
    1.24
    addClass
    1.23
     resorts
    1.23
    Resort
    1.20
    resort
    1.19
    removeClass
    1.17
     Resorts
    0.97
     resorted
    0.87
     Retreat
    0.87
    Activations Density 0.049%

    No Known Activations