© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 56581
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to computer science or programming

    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
    loroethene
    -0.47
     Union
    -0.45
     везе
    -0.44
     maju
    -0.43
     Nice
    -0.43
    rages
    -0.42
    choenen
    -0.42
    bildeten
    -0.42
     Gio
    -0.41
     Bak
    -0.40
    POSITIVE LOGITS
     special
    0.91
    special
    0.90
     differ
    0.88
     differs
    0.88
     unterscheidet
    0.83
     khusus
    0.81
     speciale
    0.80
     differed
    0.79
     specialized
    0.79
    WaitGroup
    0.78
    Activations Density 0.298%

    No Known Activations