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. 15930
    Prev
    Next
    INDEX
    Explanations

    references to individuality and personal development

    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
    RectangleBorder
    -0.60
     AppColors
    -0.56
     purpoſe
    -0.54
    BagLayout
    -0.54
     ſtate
    -0.53
     gärna
    -0.52
     houſe
    -0.52
    actéristique
    -0.52
    IMPORTED
    -0.51
     PLWABN
    -0.51
    POSITIVE LOGITS
     come
    1.04
     grow
    0.92
     go
    0.88
     emerge
    0.88
     enter
    0.83
     disappear
    0.83
     fall
    0.80
    come
    0.78
     become
    0.77
     converge
    0.77
    Activations Density 0.243%

    No Known Activations