© 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. 1453
    Prev
    Next
    INDEX
    Explanations

    code structures related to commands and configurations in utility programming

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

    technical terms related to programming or code structures

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

    code formatting and syntax

    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
     étoit
    -0.80
    UserScript
    -0.79
     EconPapers
    -0.77
    windowFixed
    -0.77
    InSection
    -0.76
    openConnection
    -0.71
     scolaires
    -0.70
    ఔ
    -0.69
     Савезне
    -0.68
    rawDesc
    -0.68
    POSITIVE LOGITS
     love
    0.41
    ar
    0.41
     Perm
    0.40
    リーの
    0.40
     zuletzt
    0.40
    Near
    0.39
     Juga
    0.39
     label
    0.39
    リー
    0.39
    i
    0.38
    Activations Density 0.007%

    No Known Activations