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. 0-GEMMASCOPE-MLP-16K
    6. 12
    Prev
    Next
    INDEX
    Explanations

    phrases related to the resolution of data or images

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to different levels of resolution in imaging or data analysis

    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-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    HtmlAttribute
    -0.97
    
    -0.85
    PerformLayout
    -0.78
    withIdentifier
    -0.77
    MemoryWarning
    -0.77
     >=",
    -0.76
     مشين
    -0.75
    RenderAtEndOf
    -0.72
    InSection
    -0.72
     []:
    -0.72
    POSITIVE LOGITS
     nocturne
    0.50
    جوا
    0.48
     obstante
    0.48
     Ebenso
    0.46
    ropo
    0.46
    Referencias
    0.46
     zná
    0.46
     many
    0.45
    EndContext
    0.45
    ebay
    0.44
    Activations Density 1.428%

    No Known Activations