© 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. 14-GEMMASCOPE-RES-16K
    11. 5230
    Prev
    Next
    INDEX
    Explanations

    the presence of markup or formatting indicators, specifically the beginning-of-sequence token and sections of segmented text in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    numerusform
    -0.76
    mergeFrom
    -0.75
    ViewStyle
    -0.71
    featureID
    -0.71
    YMMV
    -0.70
    complexContent
    -0.70
    StructEnd
    -0.69
    TintMode
    -0.69
    }{*}{
    -0.69
    </tfoot>
    -0.67
    POSITIVE LOGITS
    Autoritní
    0.83
    tagHelper
    0.81
    webpack
    0.64
    TagHelpers
    0.51
    )";
    0.51
    ИА
    0.48
    ủng
    0.48
    WEBPACK
    0.47
    الصفحه
    0.47
    Bibliograf
    0.46
    Activations Density 0.006%

    No Known Activations