© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 59374
    Prev
    Next
    INDEX
    Explanations

    instances and variations of the word "remove" and its related forms

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

    the concept of removal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndInit
    -0.80
    دانشنامهٔ
    -0.73
    invokeLater
    -0.69
    IsPostBack
    -0.64
    ⪜
    -0.64
    Rohy
    -0.63
    TypedDataSet
    -0.61
    ſelf
    -0.61
     $_"
    -0.61
     AssemblyCompany
    -0.61
    POSITIVE LOGITS
     removed
    1.54
     removal
    1.54
     remove
    1.51
     removing
    1.45
     Removal
    1.44
     Remove
    1.40
     Removing
    1.38
     REMOV
    1.36
    remove
    1.36
    Remove
    1.34
    Activations Density 0.045%

    No Known Activations