© 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. 21-GEMMASCOPE-RES-16K
    11. 14570
    Prev
    Next
    INDEX
    Explanations

    names of people, particularly in legal or formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaarangay
    -0.85
    numerusform
    -0.63
     Мексичка
    -0.60
    Personendaten
    -0.59
     AssemblyVersion
    -0.55
     complete
    -0.55
    contentLoaded
    -0.55
    LEncoder
    -0.54
     CreateTagHelper
    -0.53
    GetAsync
    -0.53
    POSITIVE LOGITS
     MonoBehaviour
    0.53
    ough
    0.52
    Brainz
    0.51
    BeginContext
    0.48
    llum
    0.48
    thenia
    0.48
     useRef
    0.47
     Sku
    0.47
    stry
    0.47
    listair
    0.47
    Activations Density 0.147%

    No Known Activations