© 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. 2-GEMMASCOPE-RES-16K
    6. 15644
    Prev
    Next
    INDEX
    Explanations

    the name "Stephen."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HttpFoundation
    -0.73
     StringTokenizer
    -0.70
    oughby
    -0.67
     Theſe
    -0.66
    altezza
    -0.65
     Duluth
    -0.63
    ății
    -0.62
    ]";
    -0.61
    ArgumentParser
    -0.61
     clazz
    -0.60
    POSITIVE LOGITS
     Stephen
    2.12
    Stephen
    1.90
     Steven
    1.74
    Steven
    1.54
     stephen
    1.53
    stephen
    1.50
     STEPHEN
    1.39
     Steve
    1.33
     Stephan
    1.19
    Steve
    1.17
    Activations Density 0.065%

    No Known Activations