© 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. 16133
    Prev
    Next
    INDEX
    Explanations

    the presence of start-of-sequence tokens

    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
     transfieras
    -0.56
     macht
    -0.54
    őbb
    -0.52
    UnknownFieldSet
    -0.52
     At
    -0.52
    <s>
    -0.52
     @"/
    -0.51
     completar
    -0.51
     P
    -0.50
    ادر
    -0.50
    POSITIVE LOGITS
     surla
    0.94
     mView
    0.77
     ViewController
    0.76
    ⤹
    0.74
     UIView
    0.73
    ніципалі
    0.73
     beginnetje
    0.72
     Viewer
    0.71
     getView
    0.70
     collectionView
    0.70
    Activations Density 0.014%

    No Known Activations