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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 110688
    Prev
    Next
    INDEX
    Explanations

    occurrences of the namespace or class definitions commonly used in programming, particularly in C++

    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
    ::
    -0.76
    SBATCH
    -0.47
     Савезне
    -0.40
     ::
    -0.38
     aVar
    -0.36
    AnchorTagHelper
    -0.35
    TypeOf
    -0.35
     يتيمه
    -0.35
    ::{
    -0.34
    %%
    -0.33
    POSITIVE LOGITS
     createState
    0.49
    ximation
    0.48
     handleMessage
    0.48
     שוליים
    0.48
     Theſe
    0.47
     marinho
    0.46
    InitVars
    0.46
     contrase
    0.46
    ⟬
    0.46
    cetines
    0.45
    Activations Density 0.006%

    No Known Activations