© 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. 7-GEMMASCOPE-RES-16K
    11. 3609
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal emotions and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     daß
    -1.09
     muß
    -0.96
     läßt
    -0.89
     guère
    -0.84
     Надо
    -0.82
    (;;)
    -0.81
     müßte
    -0.81
     Daß
    -0.75
     assai
    -0.74
     stället
    -0.73
    POSITIVE LOGITS
    GenerationType
    0.73
     impactful
    0.73
     aforementioned
    0.72
     incentiv
    0.70
    Lastly
    0.70
    Alright
    0.69
    stdc
    0.68
     Lastly
    0.66
    除此之外
    0.65
     advancements
    0.64
    Activations Density 0.323%

    No Known Activations