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. 22-GEMMASCOPE-MLP-16K
    6. 15787
    Prev
    Next
    INDEX
    Explanations

    concepts related to audience and crowd dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_mlp_out
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -1.02
     تانيه
    -0.96
    URLException
    -0.81
     مشين
    -0.75
    TagHelper
    -0.75
    الإنجليزية
    -0.73
    /*
    -0.69
     AssemblyCulture
    -0.68
    //
    -0.67
     autorytatywna
    -0.67
    POSITIVE LOGITS
     file
    0.67
    trick
    0.67
     filtered
    0.62
     stream
    0.61
     trick
    0.61
     filing
    0.59
     trickle
    0.58
    Trick
    0.58
     filter
    0.56
     filtering
    0.55
    Activations Density 0.273%

    No Known Activations