© 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. 23-GEMMASCOPE-RES-16K
    11. 14084
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes and operations in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     direta
    -0.37
    something
    -0.35
     contrário
    -0.35
    Ể
    -0.35
     Worth
    -0.34
    なもの
    -0.34
    はありません
    -0.34
     soins
    -0.33
    يديا
    -0.33
    なのが
    -0.33
    POSITIVE LOGITS
     completed
    1.57
     newly
    1.46
     acquired
    1.43
     recovered
    1.43
     extracted
    1.41
     obtained
    1.40
     downloaded
    1.38
     purchased
    1.38
     collected
    1.38
     finished
    1.35
    Activations Density 1.321%

    No Known Activations