© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8510
    Prev
    Next
    INDEX
    Explanations

    instances of parameters and names, indicating structured data definitions

    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
     '\\;'
    -0.59
     iliy
    -0.48
     Orrell
    -0.47
     verrez
    -0.46
     svårt
    -0.46
     Ceinture
    -0.45
     Ouvrez
    -0.44
     Phari
    -0.44
     automatiques
    -0.44
     devenus
    -0.44
    POSITIVE LOGITS
     оригіналу
    0.80
    tagHelperRunner
    0.78
    MemoryWarning
    0.78
    GEBURTSDATUM
    0.77
    TagMode
    0.74
     doInBackground
    0.74
    ConstraintMaker
    0.74
     iParam
    0.74
     rowspan
    0.73
     propOrder
    0.73
    Activations Density 0.028%

    No Known Activations