© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 5850
    Prev
    Next
    INDEX
    Explanations

    the word "always" and variations of it in different contexts, highlighting a focus on consistency or frequency in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     اصلا
    -0.68
     often
    -0.67
     überhaupt
    -0.65
     często
    -0.62
     artık
    -0.59
     často
    -0.58
     вовсе
    -0.56
     spesso
    -0.53
     actually
    -0.52
     altogether
    -0.52
    POSITIVE LOGITS
    KommentareTeilen
    0.58
     kasarigan
    0.57
    cky
    0.52
     wondered
    0.52
     striving
    0.51
     câte
    0.51
    onnaissance
    0.49
     пожалуйста
    0.48
     препратки
    0.46
     dreamed
    0.46
    Activations Density 0.121%

    No Known Activations