Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 1-GEMMASCOPE-MLP-16K
    6. 8945
    Prev
    Next
    INDEX
    Explanations

    monetary values represented in British pounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     £
    -2.28
    £
    -1.83
     (£
    -1.69
     €
    -1.37
    -£
    -1.34
     $\$
    -1.13
     ₹
    -1.12
     Rs
    -1.10
     (€
    -1.05
     ¥
    -0.91
    POSITIVE LOGITS
     liitty
    0.52
     apoder
    0.49
    Proportion
    0.46
     blijven
    0.45
    LLLL
    0.45
     dezelve
    0.45
     juos
    0.45
     eenig
    0.44
     ciascuno
    0.44
     juſt
    0.44
    Activations Density 0.150%

    No Known Activations