© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 10189
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a sense of excess or lack of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.77
    ]--;
    -0.68
    wußt
    -0.57
    __["
    -0.57
    orari
    -0.56
    medriver
    -0.56
    BeginContext
    -0.56
     ?>/
    -0.55
    Pautan
    -0.55
     mijne
    -0.54
    POSITIVE LOGITS
     BeautifulSoup
    0.60
    영어
    0.56
    routeProvider
    0.54
    pierw
    0.54
     disambiguazione
    0.52
     ProtoMessage
    0.52
    <td>
    0.51
    hota
    0.50
    ас
    0.50
     />\
    0.49
    Activations Density 0.062%

    No Known Activations