© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5802
    Prev
    Next
    INDEX
    Explanations

    URLs in the text

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

    Text after :// (URL beginnings)

    np_acts-logits-general · gemini-2.0-flash

    internet urls

    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
     MenuView
    -0.95
     ddelweddau
    -0.81
    orszá
    -0.75
    يكب
    -0.71
    PreferredItem
    -0.68
    AsUp
    -0.68
    
    -0.67
     متعلقه
    -0.65
    Jeografia
    -0.63
    MessageTagHelper
    -0.63
    POSITIVE LOGITS
    github
    0.94
    ://
    0.87
    www
    0.77
    twitter
    0.68
     www
    0.63
    doi
    0.63
    youtu
    0.63
    soundcloud
    0.60
    eaks
    0.53
    drive
    0.53
    Activations Density 0.044%

    No Known Activations