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. 1
    Prev
    Next
    INDEX
    Explanations

    references to deceased individuals

    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
     deceased
    -1.88
     Deceased
    -1.46
    deceased
    -1.34
     decedent
    -1.13
     verstor
    -0.83
     décé
    -0.70
     fallecido
    -0.70
     dece
    -0.69
     predeceased
    -0.69
     falle
    -0.63
    POSITIVE LOGITS
     ***!
    0.81
     utafitiHapana
    0.76
    رشف
    0.65
    XmlAccessType
    0.64
    клопе
    0.63
    AndEndTag
    0.60
    WithMany
    0.59
     pinulongan
    0.59
    +#+
    0.58
    principalColumn
    0.57
    Activations Density 0.028%

    No Known Activations