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. 15954
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to hormones and their regulation

    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
     aguja
    -0.49
     توانند
    -0.48
     emprunt
    -0.47
     تواند
    -0.46
    rália
    -0.46
     Heilig
    -0.45
     英
    -0.43
    Portail
    -0.43
    elsch
    -0.42
    freopen
    -0.42
    POSITIVE LOGITS
    GOTREF
    0.84
     lenker
    0.80
     ExecuteAsync
    0.73
    SharedCtor
    0.73
    outWeight
    0.72
    principalColumn
    0.70
    tagHelperRunner
    0.70
     שוליים
    0.69
     مشين
    0.67
    DIPSETTING
    0.66
    Activations Density 0.351%

    No Known Activations