© 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. 21-GEMMASCOPE-RES-16K
    6. 7679
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols, variables, and functions, particularly in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ])))
    -1.02
    }}}}
    -0.98
    )))),
    -0.96
    )))));
    -0.96
    ])));
    -0.94
    )))))
    -0.88
    ))));
    -0.88
    })));
    -0.88
    ])),
    -0.87
    ]))
    
    -0.84
    POSITIVE LOGITS
    localctx
    0.63
    ьогодні
    0.62
    XmlAccessorType
    0.60
    forName
    0.57
    AfterClass
    0.55
    rawDesc
    0.54
    ContentAsync
    0.53
    atoday
    0.51
    extendable
    0.51
    enity
    0.50
    Activations Density 0.851%

    No Known Activations