© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10614
    Prev
    Next
    INDEX
    Explanations

    evidence of hostile work environments and conditions that lead to harassment or abuse

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

    Hostile or abusive work environment

    np_acts-logits-general · gemini-2.0-flash

    hostile working environment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    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
    -1.02
    CloseOperation
    -0.74
     otomatig
    -0.72
    GraphicsUnit
    -0.72
     Normdatei
    -0.72
     CreateTagHelper
    -0.71
    StoryboardSegue
    -0.70
     ujednoznacz
    -0.67
    Carriera
    -0.65
    LEncoder
    -0.62
    POSITIVE LOGITS
     environment
    2.64
     environments
    2.24
    environment
    2.18
     Environment
    2.06
     ambiente
    1.96
     ENVIRONMENT
    1.95
    Environment
    1.92
     atmosphere
    1.86
     Environments
    1.80
     environ
    1.80
    Activations Density 0.582%

    No Known Activations