Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4140
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and logical operations

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

    Code-related keywords after specific symbols

    np_acts-logits-general · gemini-2.0-flash

    programming symbols and keywords

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     CGPoint
    -0.67
     IRQ
    -0.59
     eax
    -0.59
     MIP
    -0.58
     pstmt
    -0.53
     hwnd
    -0.53
     camicia
    -0.52
     irq
    -0.52
     vnode
    -0.52
     IMAP
    -0.51
    POSITIVE LOGITS
    — 
    0.83
    Hauptartikel
    0.83
    NUMX
    0.81
    setViewportView
    0.77
    MigrationBuilder
    0.77
    limsy
    0.74
    })$}
    0.73
    TagMode
    0.73
    клопе
    0.72
    hdashline
    0.72
    Activations Density 0.374%

    No Known Activations