© 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-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 12416
    Prev
    Next
    INDEX
    Explanations

    specific formatting or structure in text, such as coded functions or key indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.83
     للاسماء
    -0.80
     AssemblyCulture
    -0.76
    +#+#
    -0.74
    '][]
    -0.72
    ///</
    -0.72
    примеча
    -0.71
    (")");
    -0.70
    parsedMessage
    -0.69
     BrowserModule
    -0.69
    POSITIVE LOGITS
    _
    1.00
    __
    0.94
    ___
    0.78
     _
    0.77
    official
    0.77
    ._
    0.71
    Official
    0.71
    ____
    0.68
    ._.
    0.68
     Official
    0.67
    Activations Density 0.070%

    No Known Activations