© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 57788
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that indicate structure in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -1.00
    +#+#
    -0.97
    kháu
    -0.94
    tagHelperRunner
    -0.91
    basicConfig
    -0.86
    Tikang
    -0.86
     '\\;'
    -0.83
    aarrggbb
    -0.82
    WriteAttribute
    -0.82
    sizeCache
    -0.81
    POSITIVE LOGITS
     First
    0.57
    First
    0.51
    0.51
    `
    0.45
    ider
    0.45
     Firstly
    0.44
    首先
    0.42
     सबसे
    0.41
    idencia
    0.41
    `;
    0.40
    Activations Density 0.075%

    No Known Activations