© 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. 548
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and code structures

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

    programming terminology and syntax related to C++ Boost libraries

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

    boost mpl fusion graph

    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
     newOwner
    -0.74
    ]='\
    -0.64
    parsedMessage
    -0.63
    memset
    -0.57
     newState
    -0.56
     Uchiha
    -0.55
    copyWith
    -0.55
     strlen
    -0.53
     []:
    -0.53
     detto
    -0.52
    POSITIVE LOGITS
    honneur
    0.63
    الحياه
    0.56
     referenties
    0.53
     CURIAM
    0.51
     kasarigan
    0.49
     endeavour
    0.48
    ラク
    0.48
     Boost
    0.46
     ujednoznacz
    0.46
     Turn
    0.46
    Activations Density 0.255%

    No Known Activations