© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6240
    Prev
    Next
    INDEX
    Explanations

    elements related to the Go programming language and its error handling mechanisms

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

    Go packages and imports

    np_acts-logits-general · gemini-2.0-flash

    Go function definitions

    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
    Personensuche
    -0.42
    AndEndTag
    -0.36
    newtheorem
    -0.35
    GeneratedValue
    -0.35
    wości
    -0.34
    стями
    -0.33
     موسي
    -0.32
    Elő
    -0.32
     mignon
    -0.32
     cryst
    -0.31
    POSITIVE LOGITS
    ########.
    0.73
    sizeCache
    0.64
    MarshalTo
    0.63
    ResponseWriter
    0.59
     EconPapers
    0.59
     wireType
    0.56
     propOrder
    0.55
    VersionUID
    0.53
    endphp
    0.52
     iNdEx
    0.51
    Activations Density 0.166%

    No Known Activations