© 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-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 108909
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Convert" and its variations within contexts involving transformation or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Convert
    -1.68
    Convert
    -1.58
     convert
    -1.23
    convert
    -1.09
     converts
    -1.02
     converting
    -1.02
     Converting
    -1.00
     converted
    -0.98
     conversion
    -0.96
    Converting
    -0.94
    POSITIVE LOGITS
    HtmlAttribute
    0.58
    ValueStyle
    0.57
    webElementGuid
    0.54
    KEYCODE
    0.52
    fjspx
    0.51
    UrlEncoded
    0.51
    IVEREF
    0.50
    verifyException
    0.50
    KommentareTeilen
    0.50
    NameInMap
    0.49
    Activations Density 0.001%

    No Known Activations