© 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. 2481
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "brand" along with various instances of equality signs and attribute assignments

    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
    another
    -0.51
     another
    -0.49
     دیگری
    -0.48
    popd
    -0.47
     Kar
    -0.46
    äť
    -0.46
     ANOTHER
    -0.45
    另一
    -0.45
     additional
    -0.44
    carrying
    -0.44
    POSITIVE LOGITS
    tagHelperRunner
    0.81
     New
    0.80
    New
    0.77
     समीक्षाओं
    0.74
     financières
    0.74
    ########.
    0.73
     doInBackground
    0.72
     EconPapers
    0.68
     للاسماء
    0.67
     Newell
    0.67
    Activations Density 0.069%

    No Known Activations