Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 7298
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific measurement and analysis

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     للمعارف
    -0.81
    getObject
    -0.81
    abestanden
    -0.81
     Bots
    -0.80
     retour
    -0.79
     nakalista
    -0.78
     portatil
    -0.77
     hés
    -0.77
     inoxydable
    -0.76
    Bots
    -0.75
    POSITIVE LOGITS
    STRIP
    1.09
     STRIP
    1.05
     stripping
    0.92
     strip
    0.91
     Trix
    0.89
     fú
    0.89
     stri
    0.87
     Cur
    0.87
     Strip
    0.87
    tease
    0.86
    Activations Density 0.230%

    No Known Activations