© 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. 2-GEMMASCOPE-RES-16K
    6. 2813
    Prev
    Next
    INDEX
    Explanations

    specific references to mathematical regression tests and related programming functions

    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
     nonatomic
    -0.78
    umptive
    -0.70
    Gön
    -0.70
    lloworld
    -0.69
    setVerticalGroup
    -0.68
     Bue
    -0.68
     Trish
    -0.67
    }();
    -0.67
    kespea
    -0.66
     Cac
    -0.66
    POSITIVE LOGITS
    RegressionTest
    0.74
     McCall
    0.73
     dior
    0.72
     Pattaya
    0.69
     通販
    0.66
     oats
    0.66
     Pennington
    0.65
     Cracks
    0.65
    Daryl
    0.65
     Atti
    0.64
    Activations Density 6.867%

    No Known Activations