Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. MLP Out - 65k
    5. 4-GEMMASCOPE-MLP-65K
    6. 27
    Prev
    Next
    INDEX
    Explanations

    geographic locations and administrative divisions in Vietnam

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_4/width_65k/average_l0_66
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.4.hook_mlp_out
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageOf
    -0.69
     CreateTagHelper
    -0.65
     vacacionales
    -0.64
    Insee
    -0.60
     دیکھیے
    -0.58
    errHandler
    -0.56
    Datuak
    -0.55
     OFDb
    -0.54
    GeneratedCode
    -0.54
     дописавши
    -0.54
    POSITIVE LOGITS
     خارجية
    0.59
    principalTable
    0.57
    runOnUiThread
    0.56
     esternos
    0.52
     admixture
    0.51
     estekak
    0.51
     probability
    0.50
     الغذ
    0.50
    midler
    0.50
     automatica
    0.50
    Activations Density 0.016%

    No Known Activations