© 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. 1-GEMMASCOPE-RES-16K
    6. 8600
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "com" in various contexts

    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
     дописавши
    -0.64
     Unters
    -0.57
    ])).
    -0.57
     سكانية
    -0.57
    shadowRadius
    -0.56
    inafter
    -0.55
    Zitat
    -0.54
    HtmlAttribute
    -0.54
    clientY
    -0.54
    AddHtmlAttribute
    -0.53
    POSITIVE LOGITS
    com
    2.68
    Com
    1.77
    COM
    1.74
    coms
    1.58
     Com
    1.23
     COM
    1.11
     com
    1.05
    org
    1.01
    COMM
    0.99
    comm
    0.93
    Activations Density 0.123%

    No Known Activations