© 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. 7-GEMMASCOPE-RES-16K
    11. 6853
    Prev
    Next
    INDEX
    Explanations

    phrases that convey alternative names or identities for individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -0.59
    ArgumentParser
    -0.57
    archiviato
    -0.56
    MessageTagHelper
    -0.56
    "]();
    -0.54
    ら
    -0.53
    SharedCtor
    -0.51
     draws
    -0.48
    Abit
    -0.47
    LookAnd
    -0.47
    POSITIVE LOGITS
     nicknamed
    0.86
    __(/*!
    0.86
     AKA
    0.85
     aka
    0.83
    いわゆる
    0.82
     &___
    0.72
    enumi
    0.72
    called
    0.72
     dikenal
    0.72
     CALLED
    0.72
    Activations Density 0.157%

    No Known Activations