© 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. 22-GEMMASCOPE-RES-16K
    6. 6693
    Prev
    Next
    INDEX
    Explanations

    references to workplace environments and their dynamics, particularly focusing on hostility and the impact of leadership

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

    preceding "environment"

    np_acts-logits-general · gemini-2.0-flash

    describing an environment

    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
    rungsseite
    -1.00
    렷
    -0.74
    GraphicsUnit
    -0.70
    StoryboardSegue
    -0.69
     ujednoznacz
    -0.69
    HideFlags
    -0.62
     otomatig
    -0.62
    +#+#
    -0.61
    gwt
    -0.60
     الرياضيه
    -0.58
    POSITIVE LOGITS
     environment
    2.97
    environment
    2.49
     environments
    2.46
     Environment
    2.29
     ENVIRONMENT
    2.16
    Environment
    2.13
     ambiente
    2.11
     atmosphere
    2.05
    环境
    1.98
     environ
    1.97
    Activations Density 0.500%

    No Known Activations