© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 3858
    Prev
    Next
    INDEX
    Explanations

    closing parentheses in mathematical expressions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    بالإنجليزية
    -0.56
    féle
    -0.53
    İR
    -0.51
     elétrica
    -0.50
     bertahan
    -0.50
    ISTRATION
    -0.50
    urities
    -0.50
    pañol
    -0.50
     беремен
    -0.49
    climate
    -0.49
    POSITIVE LOGITS
    )])
    2.06
    ))),
    1.89
    )})
    1.88
    )))
    1.83
    ]))
    1.78
    ())))
    1.75
    ])))
    1.71
    ])),
    1.69
    ))))
    1.67
    }))
    1.67
    Activations Density 0.279%

    No Known Activations