© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 14575
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to maintaining or managing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 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
    zusch
    -0.70
     Choudh
    -0.69
     ruta
    -0.65
     He
    -0.64
     Sk
    -0.63
     fibras
    -0.62
     dugaan
    -0.61
     FROM
    -0.60
     To
    -0.60
     Ger
    -0.60
    POSITIVE LOGITS
    intenance
    1.36
    INTAIN
    1.34
     maintenance
    1.22
     Maintain
    1.21
    Maintain
    1.20
     maintained
    1.18
     maintain
    1.17
     raiſ
    1.14
     Maintaining
    1.14
     maintaining
    1.13
    Activations Density 0.039%

    No Known Activations