© 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. 5-GEMMASCOPE-RES-16K
    11. 1052
    Prev
    Next
    INDEX
    Explanations

    phrases that communicate simplification or generalization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kerap
    -0.59
     Uran
    -0.59
    ";
    -0.55
     Marac
    -0.55
     particolarmente
    -0.54
     Repair
    -0.53
     repaired
    -0.53
    Discre
    -0.53
     Observed
    -0.53
     amigurumi
    -0.53
    POSITIVE LOGITS
     basically
    1.75
    Basically
    1.74
    basically
    1.68
     Basically
    1.66
    Essentially
    1.51
    essentially
    1.48
     essentially
    1.47
     Essentially
    1.43
     básicamente
    1.19
    基本上
    0.86
    Activations Density 0.135%

    No Known Activations