© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1394
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming concepts and coding issues

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

    Code snippets, especially database or web-related

    np_acts-logits-general · gemini-2.0-flash

    tables with values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     groupBox
    -0.43
    yelidikan
    -0.41
     épisode
    -0.38
     onStop
    -0.38
     anteriore
    -0.38
     acredita
    -0.38
     gewöhnlich
    -0.37
     CURIAM
    -0.37
     assumes
    -0.37
    接种
    -0.37
    POSITIVE LOGITS
    SharedDtor
    0.66
    Tikang
    0.56
    MessageOf
    0.53
    
    0.47
    ChildScrollView
    0.45
    BibitemShut
    0.44
    ghijkl
    0.43
     Италијани
    0.42
     ujednoznacz
    0.42
     CallOverrides
    0.41
    Activations Density 1.212%

    No Known Activations