© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 63536
    Prev
    Next
    INDEX
    Explanations

    negative descriptions and stereotypes about social groups

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

    stereotyping and prejudice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    supp
    -0.30
     Suppl
    -0.30
     cooper
    -0.30
     MainAxisSize
    -0.30
     respecter
    -0.29
     supp
    -0.29
     total
    -0.28
    AnchorTagHelper
    -0.28
     Proceedings
    -0.28
    depending
    -0.28
    POSITIVE LOGITS
    tvguidetime
    0.70
     pinulongan
    0.62
    oredCriteria
    0.56
    verwijspagina
    0.54
    AndEndTag
    0.53
    OCCURRED
    0.52
    SharedDtor
    0.50
    出版年
    0.50
    évaluateur
    0.50
    Datuak
    0.48
    Activations Density 0.051%

    No Known Activations