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. 8
    Prev
    Next
    INDEX
    Explanations

    references to pathways or routes in a geographical context

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

    phrases indicating progression or movement “through” something, literally or figuratively, often as “make one’s way through” paths, routes, or tasks.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    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
     through
    -0.89
     THROUGH
    -0.87
    through
    -0.82
     thru
    -0.82
     Through
    -0.82
    Through
    -0.81
     través
    -0.77
    THROUGH
    -0.76
    thru
    -0.74
     gjennom
    -0.73
    POSITIVE LOGITS
     mapStateToProps
    0.66
    AnchorStyles
    0.55
     sudden
    0.50
    الصفحه
    0.48
     שוליים
    0.47
     JsonConvert
    0.47
    ặt
    0.46
    NOPQRST
    0.46
    ình
    0.46
    Whatsapp
    0.45
    Activations Density 0.205%

    No Known Activations