© 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. 33-GEMMASCOPE-RES-16K
    11. 7806
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" along with variations on the word "that," with a strong emphasis on context and usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.50
     informée
    -0.45
    ########.
    -0.45
    +#+
    -0.44
     Smarty
    -0.40
    mybatisplus
    -0.39
     سكانية
    -0.39
     Photocase
    -0.38
    Hentet
    -0.37
    alagi
    -0.37
    POSITIVE LOGITS
     houſe
    0.56
     Houſe
    0.54
     canst
    0.54
    InputBorder
    0.52
     Cæsar
    0.51
     Theſe
    0.48
     createState
    0.46
    subpackage
    0.45
     pleaſure
    0.44
    makeText
    0.43
    Activations Density 0.091%

    No Known Activations