© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11822
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.47
     superstitious
    -0.42
     alé
    -0.42
     TextEditing
    -0.41
    piram
    -0.39
     superstition
    -0.37
     пога
    -0.36
    Билгалдахарш
    -0.36
    PyErr
    -0.35
     CAG
    -0.35
    POSITIVE LOGITS
     integration
    1.05
     integrating
    0.97
     integrates
    0.96
     integrations
    0.96
     integrate
    0.93
     functionalities
    0.93
     funcionalidades
    0.90
     integrated
    0.88
     integración
    0.87
     functionality
    0.86
    Activations Density 1.316%

    No Known Activations