© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 3922
    Prev
    Next
    INDEX
    Explanations

    terms related to maintenance and stability

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

    Maintain/maintaining followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    maintaining a state or condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.85
     autorytatywna
    -0.80
    oredCriteria
    -0.80
     ujednoznacz
    -0.80
    migrationBuilder
    -0.79
     lenker
    -0.73
    windowFixed
    -0.72
    RegressionTest
    -0.69
     Réponses
    -0.69
    ⓧ
    -0.69
    POSITIVE LOGITS
     integrity
    0.95
     momentum
    0.94
     composure
    0.89
     sanity
    0.86
     continuity
    0.82
     equilibrium
    0.79
     homeostasis
    0.79
     pace
    0.78
     vigilance
    0.78
     secrecy
    0.77
    Activations Density 0.248%

    No Known Activations