© 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. 1-GEMMASCOPE-RES-16K
    11. 6398
    Prev
    Next
    INDEX
    Explanations

    references to the concept of something being lost or no longer available

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Exacts
    -0.82
    GEBURTSDATUM
    -0.80
    contentLoaded
    -0.76
     gynhyrchwyd
    -0.74
    ThroughAttribute
    -0.71
    rungsseite
    -0.69
    PostExecute
    -0.68
    URLException
    -0.68
    IUrlHelper
    -0.67
    ruptedException
    -0.66
    POSITIVE LOGITS
     glory
    0.97
    glory
    0.88
     ruin
    0.88
     chaos
    0.86
     terrible
    0.80
     gone
    0.80
     ruined
    0.79
     ruining
    0.79
     disaster
    0.78
     desastre
    0.78
    Activations Density 0.112%

    No Known Activations