© 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. 1-GEMMASCOPE-RES-16K
    11. 10154
    Prev
    Next
    INDEX
    Explanations

    references to 'Mel', likely related to contexts about melatonin or individuals with 'Mel' in their name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sonno
    -0.50
     Nachfolger
    -0.50
    onomía
    -0.49
    yny
    -0.49
     Draper
    -0.49
     label
    -0.48
     culturelles
    -0.46
    lalu
    -0.44
     Его
    -0.44
     "@/
    -0.44
    POSITIVE LOGITS
     Mel
    0.97
    Mel
    0.85
    mel
    0.82
     GE
    0.76
     Ger
    0.73
    MEL
    0.70
     ProtoMessage
    0.69
    bellum
    0.68
    Ger
    0.68
    Aria
    0.68
    Activations Density 1.850%

    No Known Activations