© 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. 11393
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistical results and significance in research studies

    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
     kteří
    -0.48
    }();
    -0.46
     Enquanto
    -0.45
    peka
    -0.44
    afficheront
    -0.44
     RISERVATA
    -0.44
    +:+
    -0.43
     Makefile
    -0.43
    ={[
    -0.43
    клопе
    -0.42
    POSITIVE LOGITS
     Episode
    1.14
     Chapter
    1.10
     Option
    1.10
     Item
    1.08
     Module
    1.07
     Section
    1.05
     Part
    1.04
     Stage
    1.03
     Version
    1.03
     Unit
    1.02
    Activations Density 2.274%

    No Known Activations