Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1992
    Prev
    Next
    INDEX
    Explanations

    sentences that include punctuation, particularly periods

    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
     Мексичка
    -1.07
    GEBURTSDATUM
    -1.06
     '\\;'
    -0.94
     Roskov
    -0.93
     Efq
    -0.91
    Diweddarwch
    -0.84
    Personendaten
    -0.83
     виправивши
    -0.81
    '])){
    
    -0.79
    </thead>
    -0.78
    POSITIVE LOGITS
    cshtml
    0.61
    으며
    0.54
    יא
    0.54
    zu
    0.50
    cocho
    0.49
     hộp
    0.49
     
    0.49
     As
    0.49
    spli
    0.48
    '
    0.48
    Activations Density 0.306%

    No Known Activations