© 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. 31-GEMMASCOPE-RES-16K
    11. 124
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Ten" and its variations or related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "Ten" appearing at the beginning of proper nouns or product names.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kreises
    -0.38
     Bagi
    -0.30
     Sociales
    -0.29
    摇摇头
    -0.29
    摇了摇头
    -0.28
     distrik
    -0.27
     financiero
    -0.26
    Nothing
    -0.26
    RegressionTest
    -0.26
    حياته
    -0.26
    POSITIVE LOGITS
     Tensor
    0.73
     nakalista
    0.70
     Tend
    0.69
     Tenn
    0.69
    AndEndTag
    0.67
    Tenn
    0.66
     Ten
    0.63
    NESSEE
    0.62
     Teng
    0.62
     فريبيس
    0.62
    Activations Density 0.206%

    No Known Activations