© 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. 23-GEMMASCOPE-RES-16K
    6. 9859
    Prev
    Next
    INDEX
    Explanations

    specific formatting or syntax patterns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invokingState
    -0.65
     виправивши
    -0.63
     autorytatywna
    -0.62
    parsedMessage
    -0.59
    ---*/
    -0.58
    djangoproject
    -0.57
     pinulongan
    -0.57
    homonymie
    -0.57
    ViewFeatures
    -0.57
    FTFY
    -0.56
    POSITIVE LOGITS
    Népesség
    0.54
    kaar
    0.54
     Peel
    0.54
    kháu
    0.49
     Prox
    0.49
    ɵ
    0.48
     cocoon
    0.47
    textwidth
    0.47
     Engra
    0.47
    Peel
    0.47
    Activations Density 0.124%

    No Known Activations