© 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. 4833
    Prev
    Next
    INDEX
    Explanations

    phrases that convey the importance of human effort, relationships, and guidance in achieving goals

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

    after "of," "through," or "to"

    np_acts-logits-general · gemini-2.0-flash

    skillful and proper methods

    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
    setViewportView
    -0.59
     facie
    -0.56
     ogóle
    -0.53
    RSpec
    -0.51
    zustellen
    -0.49
    AddField
    -0.48
    IActionResult
    -0.47
     prü
    -0.47
     problemática
    -0.47
     toàn
    -0.47
    POSITIVE LOGITS
     judicious
    1.17
     careful
    1.11
     skillful
    1.05
     clever
    1.03
     diligent
    1.00
     skilful
    0.94
     proper
    0.94
     concerted
    0.91
     cleverly
    0.91
     properly
    0.89
    Activations Density 0.556%

    No Known Activations