© 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. 11-GEMMASCOPE-RES-16K
    11. 4615
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "keep" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.57
    PerformLayout
    -0.57
    ngrx
    -0.54
     Fior
    -0.53
    onson
    -0.52
    djangoproject
    -0.52
     solution
    -0.51
     Solution
    -0.50
     FormGroup
    -0.50
     roleId
    -0.50
    POSITIVE LOGITS
    Keep
    1.56
     Keep
    1.49
    keep
    1.45
     keep
    1.44
     kept
    1.37
     keeps
    1.37
    keeps
    1.35
    Keeps
    1.34
     Keeps
    1.34
    kept
    1.32
    Activations Density 0.072%

    No Known Activations