© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29243
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and specific entities

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

    names and institutions

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Betts
    -0.71
     Haines
    -0.69
    Meli
    -0.66
    Bbb
    -0.64
    o
    -0.63
    ɲ
    -0.63
     Caruso
    -0.61
     Landis
    -0.60
     signes
    -0.59
    Dias
    -0.58
    POSITIVE LOGITS
    complexContent
    1.08
     Administrativna
    0.90
    клопе
    0.87
    WithIOException
    0.87
    Données
    0.84
    ]$}
    0.84
     CURIAM
    0.84
     Pars
    0.82
     Scra
    0.81
     Parity
    0.81
    Activations Density 0.452%

    No Known Activations