© 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. 7953
    Prev
    Next
    INDEX
    Explanations

    terms related to surveillance and investigation

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

    Brazilian politics/government

    np_acts-logits-general · gemini-2.0-flash

    Research Foundation, Federal University, Health Program

    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
    áñez
    -0.43
     mema
    -0.43
     ervan
    -0.42
     eléctrico
    -0.41
     talál
    -0.39
     kesan
    -0.38
     directos
    -0.38
     sendi
    -0.37
     «
    -0.37
    弾
    -0.37
    POSITIVE LOGITS
     Infórmanos
    1.00
     Efq
    1.00
    tvguidetime
    0.98
    ">//
    0.94
     NSCoder
    0.93
     CreateTagHelper
    0.88
    enterOuterAlt
    0.87
    ///</
    0.85
    enumi
    0.85
     Monfieur
    0.85
    Activations Density 0.181%

    No Known Activations