© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 445
    Prev
    Next
    INDEX
    Explanations

    references to specific brands, services, or products

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

    references to web addresses and links related to updates

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

    dejal, ZampleBox, F1, Qasim, CNET, VPN

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     resourceCulture
    -0.77
     GenerationType
    -0.65
    antMatchers
    -0.60
    MemoryWarning
    -0.54
    
    -0.53
    izamos
    -0.51
    Saluti
    -0.51
    ########.
    -0.51
     mait
    -0.51
    awakeFromNib
    -0.51
    POSITIVE LOGITS
     Jio
    0.57
     Targ
    0.52
     Babyl
    0.51
     chré
    0.50
     Guarda
    0.47
    RegressionTest
    0.47
     Inbox
    0.46
    droid
    0.46
    pinch
    0.46
     monopo
    0.45
    Activations Density 0.152%

    No Known Activations