© 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. 18-GEMMASCOPE-RES-16K
    6. 4120
    Prev
    Next
    INDEX
    Explanations

    phrases related to political advice and commentary

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

    preceding names

    np_acts-logits-general · gemini-2.0-flash

    celebrities and public figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.68
     Aline
    -0.64
     BoxFit
    -0.63
     Arcadia
    -0.61
    期刊论文
    -0.60
     Mawr
    -0.58
     Helga
    -0.58
     dessus
    -0.55
     vastaan
    -0.54
    Janice
    -0.54
    POSITIVE LOGITS
     superstar
    0.77
     former
    0.66
     President
    0.63
     actor
    0.63
     billionaire
    0.62
     superstars
    0.62
     celebrities
    0.58
     Obama
    0.58
     singer
    0.58
     Barack
    0.57
    Activations Density 1.089%

    No Known Activations