© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 2795
    Prev
    Next
    INDEX
    Explanations

    code structure and formatting elements in programming languages

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

    Characters used in code or identifiers

    np_acts-logits-general · gemini-2.0-flash

    *** markers and technical snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlEnum
    -0.71
    mybatisplus
    -0.68
    ConverterFactory
    -0.67
     Chwiliwch
    -0.67
    PhysRevLett
    -0.67
     censiti
    -0.66
    CppCodeGen
    -0.66
     TokenType
    -0.64
    setupUi
    -0.64
    interopRequire
    -0.63
    POSITIVE LOGITS
    unnitel
    0.41
    Anch
    0.41
     acciaio
    0.40
    Propel
    0.40
     brig
    0.40
     Anch
    0.40
     Entomol
    0.39
    izzati
    0.39
     camicia
    0.38
     itin
    0.38
    Activations Density 0.002%

    No Known Activations