© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12523
    Prev
    Next
    INDEX
    Explanations

    coding syntax and elements related to error handling in programming

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

    Code, file paths, and programming errors

    np_acts-logits-general · gemini-2.0-flash

    file and line number markers

    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
    Tikang
    -0.63
    ArgsConstructor
    -0.52
    TabIndex
    -0.45
    HasAnnotation
    -0.44
     برانيه
    -0.43
     arrangement
    -0.43
    arrangement
    -0.43
    interopRequire
    -0.42
    TemporalType
    -0.42
     createSlice
    -0.42
    POSITIVE LOGITS
     Italijani
    0.50
    ISupport
    0.44
    랬
    0.43
     llamaba
    0.42
     veroor
    0.41
     sucedido
    0.41
     ocurrió
    0.39
     consciência
    0.39
    lineno
    0.38
     oídos
    0.37
    Activations Density 0.338%

    No Known Activations