Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 807
    Prev
    Next
    INDEX
    Explanations

    references to social justice issues and inequalities

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

    discussions around personal responsibility and societal issues

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

    groups of people and society

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ➟
    -0.67
    GOTREF
    -0.67
     виправивши
    -0.66
     unexpectedly
    -0.61
     possibles
    -0.59
     disponibilités
    -0.59
    OGND
    -0.58
     redan
    -0.56
     fizer
    -0.56
     possibili
    -0.55
    POSITIVE LOGITS
     politicians
    0.89
     society
    0.82
     people
    0.78
     governments
    0.78
     deberían
    0.77
     government
    0.68
     humans
    0.68
     debería
    0.67
     Governments
    0.66
     dovrebbero
    0.65
    Activations Density 0.307%

    No Known Activations