© 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. 22-GEMMASCOPE-RES-16K
    11. 14447
    Prev
    Next
    INDEX
    Explanations

    references to leadership styles and their impact on teamwork and organizational culture

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

    Academic or research-related texts

    np_acts-logits-general · gemini-2.0-flash

    research and study

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lably
    -0.63
     ANYTHING
    -0.58
     exquisitely
    -0.58
     specs
    -0.58
    FIX
    -0.57
    cipar
    -0.57
     ANYONE
    -0.57
     prettiest
    -0.56
     cools
    -0.56
     EVERYTHING
    -0.56
    POSITIVE LOGITS
     research
    0.81
     researcher
    0.80
     study
    0.76
     perceptions
    0.75
     empirical
    0.69
     perceived
    0.69
     theoretical
    0.69
     socio
    0.69
     conceptual
    0.67
     estudia
    0.67
    Activations Density 0.663%

    No Known Activations