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. 6-GEMMASCOPE-MLP-16K
    6. 98
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "David Sinclair."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.86
    +#+#
    -0.85
    #+#
    -0.83
     activity
    -0.80
     CreateTagHelper
    -0.79
    activity
    -0.79
     SwitchCompat
    -0.78
    ItemBackground
    -0.74
    الإنجليزية
    -0.74
     ACTIVITY
    -0.73
    POSITIVE LOGITS
     steht
    0.45
    DIP
    0.42
    طل
    0.41
     Sand
    0.40
    ējās
    0.40
    ヶ
    0.40
    apu
    0.40
    isip
    0.39
    genic
    0.38
     sẻ
    0.38
    Activations Density 0.648%

    No Known Activations