© 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. 3-GEMMASCOPE-RES-16K
    11. 2431
    Prev
    Next
    INDEX
    Explanations

    terms related to community composition and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.58
     borrowed
    -0.56
     slightest
    -0.51
    效
    -0.50
     préalable
    -0.50
     Paral
    -0.49
     finitely
    -0.49
     calore
    -0.49
     chấm
    -0.47
     Theſe
    -0.47
    POSITIVE LOGITS
     AspNetCore
    0.93
    composition
    0.78
    ReusableCell
    0.78
     composition
    0.77
     demographics
    0.76
    Demographics
    0.74
    ztály
    0.74
     distribution
    0.74
    новништво
    0.73
     proportions
    0.73
    Activations Density 1.083%

    No Known Activations