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. 25
    Prev
    Next
    INDEX
    Explanations

    references to buyers and sellers in a transactional context

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

    terms related to buyers and sellers in a commercial context

    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
     buyer
    -0.82
     buyers
    -0.69
     seller
    -0.60
    buyer
    -0.59
     Buyer
    -0.59
     purchaser
    -0.56
     Protección
    -0.54
    влечения
    -0.54
     Murray
    -0.52
    Hill
    -0.52
    POSITIVE LOGITS
    BeginContext
    0.88
     препратки
    0.74
    DotNetBar
    0.73
     nocturna
    0.68
    stdc
    0.67
    nemonic
    0.67
    requestCode
    0.66
     mahi
    0.66
     kaarangay
    0.65
     Samar
    0.65
    Activations Density 0.159%

    No Known Activations