© 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. 20-GEMMASCOPE-RES-16K
    11. 12305
    Prev
    Next
    INDEX
    Explanations

    valuable data related to events or actions involving rights, particularly in the context of social or political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text followed by "by" or "Pro" or "Authorities"

    np_acts-logits-general · gemini-2.0-flash

    race or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IBOutlet
    -0.51
     EClass
    -0.48
    ))[
    -0.44
    ={`/
    -0.44
    makeText
    -0.43
    }`
    -0.43
     {}));
    -0.42
    iffel
    -0.41
    }{*}{
    -0.40
    PREFERRED
    -0.40
    POSITIVE LOGITS
    WASHINGTON
    0.90
    By
    0.87
     Monfieur
    0.78
     WASHINGTON
    0.77
     themſelves
    0.75
     By
    0.74
     Jefus
    0.73
     Redacción
    0.72
     itſelf
    0.72
     purpoſe
    0.71
    Activations Density 0.150%

    No Known Activations