© 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. 15-GEMMASCOPE-RES-16K
    11. 13240
    Prev
    Next
    INDEX
    Explanations

    punctuation and syntax elements in code or markup

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    e
    -1.12
    ed
    -1.05
    ه
    -0.83
    onde
    -0.79
    ي
    -0.79
    i
    -0.78
    2
    -0.73
    нке
    -0.73
    wara
    -0.71
    io
    -0.71
    POSITIVE LOGITS
    __':
    1.46
    ]))
    1.39
    __":
    1.38
    ']))
    1.37
    ()))
    1.36
    '])){
    1.31
    }")
    1.30
    '))
    1.30
    '},
    1.28
    ]){
    1.26
    Activations Density 0.040%

    No Known Activations