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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 109210
    Prev
    Next
    INDEX
    Explanations

    aspects of mathematical or programming syntax

    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
    AutoresizingMask
    -0.57
    Procedure
    -0.50
     disambiguazione
    -0.49
    protoimpl
    -0.49
     useNavigate
    -0.48
    PROCEDURE
    -0.48
     procedure
    -0.47
     assurent
    -0.46
    #+#
    -0.45
    SuppressLint
    -0.45
    POSITIVE LOGITS
     câte
    0.40
     popraw
    0.39
     fijo
    0.38
     mię
    0.38
     problemu
    0.38
    ientôt
    0.37
     Ausrüstung
    0.36
     desecha
    0.36
     toalha
    0.35
     régal
    0.35
    Activations Density 0.257%

    No Known Activations