© 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. 5-GEMMASCOPE-RES-16K
    11. 6639
    Prev
    Next
    INDEX
    Explanations

    state-related phrases or descriptors about entities, particularly focusing on their characteristics or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gobier
    -0.54
    ύ
    -0.52
    ma
    -0.51
     prefeito
    -0.51
     gereken
    -0.51
     créativité
    -0.51
     bì
    -0.51
     Zufall
    -0.50
    最快更新
    -0.49
     survie
    -0.49
    POSITIVE LOGITS
     Audiodateien
    0.75
     المعيارى
    0.71
     चीज़ों
    0.69
    цездатний
    0.68
    脚注の使い方
    0.68
    displaymath
    0.66
    devamını
    0.65
    >--}}
    0.63
    extAlignment
    0.61
    pyx
    0.61
    Activations Density 0.280%

    No Known Activations