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. 1-GEMMASCOPE-MLP-16K
    6. 8900
    Prev
    Next
    INDEX
    Explanations

    references to devices and their components

    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
     device
    -2.77
     devices
    -2.44
     Device
    -2.41
    device
    -2.33
     Devices
    -2.31
    Device
    -2.20
     DEVICE
    -2.03
    devices
    -2.02
    Devices
    -1.94
     DEVICES
    -1.74
    POSITIVE LOGITS
    esModule
    0.54
     DriverManager
    0.54
    )))));
    0.54
    賀状
    0.53
     userManager
    0.52
    }$.\\
    0.52
    Abitanti
    0.50
    writeField
    0.50
     transfieras
    0.49
     officielles
    0.48
    Activations Density 0.141%

    No Known Activations