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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 56767
    Prev
    Next
    INDEX
    Explanations

    syntactic elements and structures in code snippets

    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
    RetentionPolicy
    -0.78
     دیکھیے
    -0.70
    клопе
    -0.69
    sizeCache
    -0.65
     &___
    -0.65
    MessageOf
    -0.64
     Daß
    -0.64
    verwijspagina
    -0.64
     betweenstory
    -0.62
     AssemblyTitle
    -0.61
    POSITIVE LOGITS
     final
    0.60
    schedulers
    0.52
     future
    0.50
    rawDesc
    0.49
    OwnProperty
    0.48
    iade
    0.48
     NSCoder
    0.47
    ATES
    0.47
    dafx
    0.47
     done
    0.45
    Activations Density 0.007%

    No Known Activations