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. 15951
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical processes and interactions in nanoparticle synthesis

    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
    MemoryWarning
    -0.56
    ✎
    -0.54
    ukseen
    -0.51
    oa̍t
    -0.51
    uksessa
    -0.50
     miseria
    -0.49
    CELLANEOUS
    -0.49
     Urqu
    -0.49
     Manip
    -0.48
     acceptance
    -0.47
    POSITIVE LOGITS
     مشين
    0.65
    ########.
    0.65
    */].
    0.57
    الإنجليزية
    0.57
    sizeCache
    0.56
    aarrggbb
    0.55
    äuser
    0.55
    awaiter
    0.53
     ?>>
    0.51
    NUMX
    0.50
    Activations Density 1.318%

    No Known Activations