© 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. 571
    Prev
    Next
    INDEX
    Explanations

    signs of conditional logic and programming syntax

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

    instances of the closing brace character and occurrences of the word "in."

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

    code contexts and programming constructions

    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
     queen
    -0.43
     inv
    -0.40
     konge
    -0.39
    nigh
    -0.38
     credential
    -0.38
     nigh
    -0.37
    OutOf
    -0.37
     setCurrent
    -0.37
     gọn
    -0.36
     elétrica
    -0.35
    POSITIVE LOGITS
     GenerationType
    0.99
     CreateTagHelper
    0.95
    Geplaatst
    0.92
     ویکی‌پدیا
    0.86
    fromnode
    0.84
     MaterialApp
    0.80
    EndContext
    0.80
    BeginContext
    0.78
    +#+
    0.78
    enumi
    0.77
    Activations Density 0.025%

    No Known Activations