© 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 - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 8513
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to public acknowledgment and revelation

    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
    gebracht
    -0.58
    pruch
    -0.55
    GeneratedMessage
    -0.53
     trữ
    -0.53
     başına
    -0.52
    PointerException
    -0.52
     alambre
    -0.52
    новниш
    -0.51
    ----</
    -0.51
    ionage
    -0.51
    POSITIVE LOGITS
     publicly
    1.26
     öffentlich
    1.02
     public
    1.01
     publicized
    0.96
     publici
    0.96
     publi
    0.94
     pública
    0.90
     públicas
    0.81
     publico
    0.81
    公开
    0.80
    Activations Density 0.356%

    No Known Activations