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. 1116
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to legal reviews and their criteria

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

    phrases related to legal criteria and decisions

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

    change in conditions

    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
    IsPostBack
    -0.48
    TestBed
    -0.48
    ipedi
    -0.47
    <bos>
    -0.47
    ngdoc
    -0.46
    ждены
    -0.45
    leştir
    -0.45
    mannian
    -0.45
    Достоинства
    -0.45
     تانيه
    -0.45
    POSITIVE LOGITS
     circumstances
    1.10
     attitudes
    1.05
     Circumstances
    0.99
     circonstances
    0.89
     tastes
    0.88
     Attitudes
    0.87
     fortunes
    0.87
     perceptions
    0.82
     conditions
    0.80
     things
    0.78
    Activations Density 0.108%

    No Known Activations