© 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. 17-GEMMASCOPE-RES-16K
    11. 11652
    Prev
    Next
    INDEX
    Explanations

    references or citations to authoritative sources within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hochspringen
    -0.79
     tarjo
    -0.65
    خواندن
    -0.64
     typelib
    -0.64
    principalTable
    -0.61
    kfree
    -0.61
    hermosa
    -0.61
     ervoor
    -0.61
    PathParam
    -0.60
     Superhost
    -0.59
    POSITIVE LOGITS
     reports
    0.74
     legend
    0.71
     sources
    0.69
    Selon
    0.68
    Según
    0.67
     kasarigan
    0.66
     experts
    0.63
     recent
    0.63
     analysts
    0.62
     estimates
    0.62
    Activations Density 0.093%

    No Known Activations