© 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. 16-GEMMASCOPE-RES-16K
    11. 2810
    Prev
    Next
    INDEX
    Explanations

    references to technical concepts related to engineering and health administration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    before specific nouns

    np_acts-logits-general · gemini-2.0-flash

    health, media, education, and law terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tetto
    -0.55
    ³/
    -0.54
    }))
    -0.48
     πρά
    -0.47
    })}$
    -0.47
    beginPath
    -0.47
     Inscrivez
    -0.46
     pájaros
    -0.46
    IBOutlet
    -0.46
     alluminio
    -0.46
    POSITIVE LOGITS
    RegistryLite
    0.84
    TintMode
    0.82
    TargetException
    0.77
    uxxxx
    0.77
     Italijanski
    0.75
    Portail
    0.74
     cherchés
    0.73
     alike
    0.73
    KommentareTeilen
    0.72
     שוליים
    0.72
    Activations Density 0.886%

    No Known Activations