© 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. 21-GEMMASCOPE-RES-16K
    11. 12056
    Prev
    Next
    INDEX
    Explanations

    phrases or contexts indicating intense emotions, particularly related to affection or passion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ворота
    -0.64
    ariConfig
    -0.53
     chapéu
    -0.53
    SBATCH
    -0.52
    aarrggbb
    -0.52
     peup
    -0.52
    awaiter
    -0.51
     Judge
    -0.51
     Crossroads
    -0.50
    ècie
    -0.50
    POSITIVE LOGITS
     kiss
    1.44
     kisses
    1.38
     hug
    1.36
     kissed
    1.31
     hugging
    1.28
     hugged
    1.26
     hugs
    1.24
     kissing
    1.24
     Kiss
    1.14
    hug
    1.13
    Activations Density 0.191%

    No Known Activations