© 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. 22691
    Prev
    Next
    INDEX
    Explanations

    symbols indicating strong emphasis or important points

    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
     FormsModule
    -0.82
    :✨
    -0.77
     تكبرها
    -0.70
     prefent
    -0.68
    swire
    -0.63
     Ress
    -0.63
    astify
    -0.62
    tvguidetime
    -0.62
     ftate
    -0.61
    Šaltiniai
    -0.60
    POSITIVE LOGITS
     etc
    0.85
    etc
    0.72
    ↵↵
    0.65
    jsxFileName
    0.64
     and
    0.63
    <eos>
    0.59
    [toxicity=0]
    0.57
     فريبيس
    0.54
    <h3>
    0.52
    Etc
    0.52
    Activations Density 0.065%

    No Known Activations