© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 108556
    Prev
    Next
    INDEX
    Explanations

    function return statements and error handling commands

    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
    return
    -0.44
    期刊论文
    -0.43
     return
    -0.40
     ret
    -0.40
    dAtA
    -0.40
    timos
    -0.40
     conven
    -0.36
     ligiloj
    -0.34
    HomeAsUpEnabled
    -0.33
    millimeters
    -0.33
    POSITIVE LOGITS
     ujednoznacz
    0.68
    wiſe
    0.57
     Bewußt
    0.55
    ⟬
    0.53
     itſelf
    0.53
     ब्रेकडाउन
    0.52
     ainfi
    0.51
     purpoſe
    0.50
     houſe
    0.50
     raiſ
    0.50
    Activations Density 0.002%

    No Known Activations