© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14730
    Prev
    Next
    INDEX
    Explanations

    LaTeX structure and formatting commands within documents

    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
    ########.
    -1.19
    AsUp
    -0.99
    endpush
    -0.97
     BorderRadius
    -0.97
    Vidite
    -0.97
    AddTagHelper
    -0.91
    encodeWith
    -0.89
    SharedDtor
    -0.87
    InitVars
    -0.86
     Italijani
    -0.86
    POSITIVE LOGITS
    ↵
    0.90
    }
    0.66
    )
    0.51
    :
    0.45
    ]
    0.43
    0.41
    0.41
    ↵↵↵
    0.40
    </h2>
    0.40
    </h4>
    0.39
    Activations Density 0.126%
    No Known Activations