© 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. 1318
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical and mechanical connections and components

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

    mechanical components and their connections in plumbing systems

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

    quick connect or coupling parts

    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
     تضيفلها
    -0.65
    Hentet
    -0.64
    ContentAsync
    -0.61
     ModelExpression
    -0.59
     <<<<<<<<<<<<<<
    -0.59
    AnchorTagHelper
    -0.56
     Roskov
    -0.55
    GraphicsUnit
    -0.55
     ویکی‌پدیای
    -0.55
    providedIn
    -0.54
    POSITIVE LOGITS
     connectors
    1.30
     connector
    1.29
     connections
    1.08
     connection
    1.07
     Connector
    1.06
     connecter
    1.03
     Connectors
    1.00
     conector
    0.98
    conne
    0.96
     connect
    0.96
    Activations Density 0.292%

    No Known Activations