© 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. 747
    Prev
    Next
    INDEX
    Explanations

    references to programming functions and their parameters

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

    programming-related function definitions and interactions

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

    programming code

    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
     disambiguazione
    -0.92
     wireType
    -0.89
    SequentialGroup
    -0.87
     nahilalakip
    -0.82
    StoryboardSegue
    -0.76
     ostavi
    -0.74
     EconPapers
    -0.74
     Biôgrafia
    -0.73
     تضيفلها
    -0.71
    basicConfig
    -0.71
    POSITIVE LOGITS
     moll
    0.51
    **
    0.43
    揄
    0.41
     certiorari
    0.41
    ritation
    0.40
     kvar
    0.39
    hangi
    0.39
     döner
    0.39
    getter
    0.38
    يب
    0.38
    Activations Density 0.031%

    No Known Activations