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 - 16k
    5. 0-GEMMASCOPE-MLP-16K
    6. 48
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "work" or labor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to "work" 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 @ 0-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     work
    -1.04
     working
    -0.94
     worked
    -0.76
    working
    -0.73
     WORKING
    -0.69
    {{/
    -0.65
     trabalhar
    -0.65
     trabajar
    -0.64
     Working
    -0.63
    Working
    -0.63
    POSITIVE LOGITS
    houettes
    0.63
     createState
    0.58
    CloseOperation
    0.57
    RefreshLayout
    0.56
    amship
    0.55
    bkz
    0.55
    StrictEqual
    0.54
    modelBuilder
    0.53
    HttpPut
    0.53
     CURIAM
    0.52
    Activations Density 0.097%

    No Known Activations