© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2644
    Prev
    Next
    INDEX
    Explanations

    phrases related to division and segmentation

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

    splitting or dividing

    np_acts-logits-general · gemini-2.0-flash

    divide or split into parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lccn
    -0.59
     consultato
    -0.57
    httphttps
    -0.54
     NavController
    -0.51
    原始内容存档于
    -0.50
    Ссылки
    -0.50
     препратки
    -0.50
    Données
    -0.49
    SuccessListener
    -0.48
    sant
    -0.48
    POSITIVE LOGITS
     split
    1.15
     Split
    1.01
     splitting
    0.98
     divide
    0.97
    Split
    0.94
    split
    0.94
     divides
    0.91
     division
    0.90
     splits
    0.90
     dividing
    0.89
    Activations Density 0.392%

    No Known Activations