© 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. 15876
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to scientific and medical terms

    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
    PreferredItem
    -0.84
     Kell
    -0.67
     Viel
    -0.66
     ide
    -0.65
     Balboa
    -0.65
     Lark
    -0.64
     Stimm
    -0.64
     Ide
    -0.63
     Kem
    -0.63
    part
    -0.63
    POSITIVE LOGITS
     Wittenberg
    0.85
    silian
    0.76
     Jind
    0.73
     Insulation
    0.72
     Hohen
    0.70
    })));
    0.70
     Jarrett
    0.69
    بوابة
    0.69
    Morgen
    0.68
    })()
    0.68
    Activations Density 2.859%

    No Known Activations