© 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. 19-GEMMASCOPE-RES-16K
    11. 1127
    Prev
    Next
    INDEX
    Explanations

    different numeric patterns or sequences within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ".
    -0.89
     становника
    -0.84
    "):
    -0.82
     كومونز
    -0.79
    abilia
    -0.78
     InputDecoration
    -0.77
    )";
    -0.77
    riwal
    -0.77
    )");
    -0.77
    NUMX
    -0.76
    POSITIVE LOGITS
    0
    1.16
    5
    1.05
    9
    1.05
    8
    1.05
    1
    1.04
    2
    1.04
    4
    1.03
    7
    1.02
    3
    1.01
    6
    1.00
    Activations Density 3.769%

    No Known Activations