© 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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 2699
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or symbols, particularly those related to functions and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -0.91
     fevere
    -0.91
     Efq
    -0.86
     Monfieur
    -0.84
     Wap
    -0.81
     uſed
    -0.78
     myſelf
    -0.77
     getLayout
    -0.77
     Sycamore
    -0.76
     Alger
    -0.76
    POSITIVE LOGITS
     },
    1.12
     }),
    1.05
     });
    1.02
     })
    1.01
     };
    1.00
     };
    
    0.99
     </
    0.99
     )
    0.97
     }));
    0.90
     ]
    0.90
    Activations Density 0.224%

    No Known Activations