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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 39412
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation marks in URLs or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteBarrier
    -0.63
    cdnjs
    -0.54
    ยน
    -0.53
    aglia
    -0.52
    TagMode
    -0.52
    <eos>
    -0.51
     bekijken
    -0.47
    )))
    
    -0.46
    )))
    -0.46
    istin
    -0.45
    POSITIVE LOGITS
     autorytatywna
    0.80
     الدولى
    0.74
    ITest
    0.72
     Италијани
    0.70
     bershka
    0.68
     HTS
    0.65
    MLLoader
    0.65
    ंदीखरीदारी
    0.65
     Monfieur
    0.65
     Bany
    0.64
    Activations Density 0.001%

    No Known Activations