© 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. 15-GEMMASCOPE-RES-16K
    11. 6519
    Prev
    Next
    INDEX
    Explanations

    phrases indicating gratitude or requests for assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reporter
    -0.45
    numerusform
    -0.43
    Interview
    -0.40
     nobis
    -0.39
     tan
    -0.37
     جان
    -0.37
     par
    -0.36
    над
    -0.36
    reg
    -0.36
    ான்
    -0.36
    POSITIVE LOGITS
     forum
    0.97
     threads
    0.91
     forums
    0.89
     Forumite
    0.88
     replies
    0.88
     thread
    0.88
     Forum
    0.87
     FORUM
    0.86
    Forum
    0.85
     Forums
    0.83
    Activations Density 0.493%

    No Known Activations