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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 6720
    Prev
    Next
    INDEX
    Explanations

    structural elements and formatting in written text, typically in technical or mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.75
    DockStyle
    -0.62
    tikzpicture
    -0.61
    NullCheck
    -0.60
    曖昧さ回避
    -0.60
     disambiguazione
    -0.57
     дописавши
    -0.57
    ValueStyle
    -0.56
    HasAnnotation
    -0.55
     تضيفلها
    -0.55
    POSITIVE LOGITS
     fédé
    0.73
    contentLoaded
    0.63
     africain
    0.61
    '){
    
    0.61
    =[]
    
    0.60
    ]._
    0.60
     présidenti
    0.59
     ';
    
    0.59
    ':
    
    0.59
    PreferredItem
    0.58
    Activations Density 0.756%

    No Known Activations