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-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109850
    Prev
    Next
    INDEX
    Explanations

    locations related to outdoor or natural settings, especially beaches and hills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     seaside
    -1.31
     Seaside
    -1.19
     seashore
    -0.78
     riverside
    -0.69
     coastal
    -0.58
    Coastal
    -0.49
     beachfront
    -0.48
     Coastal
    -0.48
     Lakeside
    -0.47
    seas
    -0.44
    POSITIVE LOGITS
    NameInMap
    0.96
    RenderAtEndOf
    0.85
     betweenstory
    0.81
     Wikimedijinoj
    0.78
     ujednoznacz
    0.70
     समीक्षाओं
    0.66
     kasarigan
    0.64
    蚪
    0.63
    ьаж
    0.62
    ksikon
    0.62
    Activations Density 0.001%

    No Known Activations