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. 0-GEMMASCOPE-MLP-65K
    6. 61003
    Prev
    Next
    INDEX
    Explanations

    references to a specific medical condition affecting the skin

    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-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    bor
    -1.59
     bor
    -1.08
    BOR
    -0.89
    Bor
    -0.81
     Bor
    -0.66
    sstream
    -0.65
    VIAF
    -0.56
    فس
    -0.56
    boru
    -0.56
    skyl
    -0.55
    POSITIVE LOGITS
    BufferException
    0.72
    galus
    0.71
    ergies
    0.71
    felves
    0.71
     betweenstory
    0.69
    abestanden
    0.69
     chofe
    0.68
     themſelves
    0.68
     Seeder
    0.68
    ^(@)
    0.66
    Activations Density 0.010%

    No Known Activations