© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. MLP Out - 16k
    9. 19-GEMMASCOPE-MLP-16K
    11. 8382
    Prev
    Next
    INDEX
    Explanations

    pivotal actions and results in a process, particularly those that simplify complex ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_mlp_out
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proib
    -0.51
    كذا
    -0.49
    $_['
    -0.48
    lní
    -0.47
    AxisAlignment
    -0.47
     dringend
    -0.45
    ENSIS
    -0.44
    ILLON
    -0.43
     double
    -0.43
    meyen
    -0.43
    POSITIVE LOGITS
     reduced
    1.46
     Reduced
    1.34
    reduced
    1.28
    Reduced
    1.28
     reduction
    1.27
     Reducing
    1.23
     reducing
    1.23
     reduces
    1.23
     Reduction
    1.22
     reduce
    1.21
    Activations Density 0.493%

    No Known Activations