© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. MLP Out - 16k
    9. 19-GEMMASCOPE-MLP-16K
    11. 8251
    Prev
    Next
    INDEX
    Explanations

    questions or statements that express doubt or concern about various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_mlp_out
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lood
    -0.51
     énergétique
    -0.51
    ApiOperation
    -0.49
    <>
    -0.47
     politi
    -0.46
     autoridad
    -0.46
     跳转至
    -0.46
    ipedi
    -0.45
    Hard
    -0.44
     harde
    -0.44
    POSITIVE LOGITS
    andExpect
    0.69
     CreateTagHelper
    0.68
    AndEndTag
    0.66
     समीक्षक
    0.61
    enchymal
    0.61
    RenderAtEndOf
    0.60
    MethodManager
    0.59
    CppMethod
    0.58
     jsPsych
    0.58
    DoubleQuotes
    0.57
    Activations Density 0.154%

    No Known Activations