© 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. 34-GEMMASCOPE-RES-16K
    11. 9474
    Prev
    Next
    INDEX
    Explanations

    various forms and usages of the verb "to be" and related participles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.51
    pogon
    -0.49
    TagHelper
    -0.47
    SceneManagement
    -0.45
    fjspx
    -0.45
    rams
    -0.44
    rawDesc
    -0.44
    rschein
    -0.43
    allax
    -0.43
    Autoritní
    -0.43
    POSITIVE LOGITS
     unui
    1.05
     dintr
    1.03
     unei
    0.97
     einer
    0.96
     eines
    0.90
     într
    0.86
     einem
    0.84
     toa
    0.78
     Sebuah
    0.71
    在一个
    0.68
    Activations Density 0.859%

    No Known Activations