© 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. 1481
    Prev
    Next
    INDEX
    Explanations

    concepts related to abusive or hostile work environments and support systems for victims of harassment

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

    preceding "work environment"

    np_acts-logits-general · gemini-2.0-flash

    work environment

    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
    rungsseite
    -0.85
     ujednoznacz
    -0.77
    렷
    -0.75
     الرياضيه
    -0.68
     متعلقه
    -0.67
    StoryboardSegue
    -0.65
     onData
    -0.58
     autorytatywna
    -0.56
     otomatig
    -0.56
    +#+#
    -0.55
    POSITIVE LOGITS
     environment
    3.21
    environment
    2.69
     environments
    2.55
     Environment
    2.49
     ENVIRONMENT
    2.36
    Environment
    2.33
     environnement
    2.19
     ambiente
    2.19
     environ
    2.19
    环境
    2.17
    Activations Density 0.576%

    No Known Activations