© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 726
    Prev
    Next
    INDEX
    Explanations

    instances and phrases related to amendments and procedural aspects in legal contexts

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

    the presence of specific initial tokens in text, suggesting it looks for structured or formatted entries

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

    during a period

    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
     photolibrary
    -1.01
     Majefty
    -0.94
     greateſt
    -0.92
     myſelf
    -0.91
     pleaſure
    -0.90
     Houſe
    -0.89
     Efq
    -0.88
     ་་
    -0.88
     leſs
    -0.86
     itſelf
    -0.86
    POSITIVE LOGITS
    ⓧ
    0.84
    uxxxx
    0.68
     ujednoznacz
    0.64
    KommentareTeilen
    0.61
    曖昧さ回避
    0.55
    rungsseite
    0.53
     autorytatywna
    0.50
     CreateTagHelper
    0.50
     hela
    0.49
     ou
    0.47
    Activations Density 0.312%

    No Known Activations