© 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. 39-GEMMASCOPE-RES-16K
    11. 2514
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and efficiency in item identification and processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.58
     CreateTagHelper
    -0.54
     betweenstory
    -0.54
    neté
    -0.48
    GOTREF
    -0.48
    uxxxx
    -0.47
     Италијани
    -0.47
    WindowConstants
    -0.47
    webElementXpaths
    -0.46
    rrggbb
    -0.46
    POSITIVE LOGITS
     saves
    1.66
     saving
    1.55
     eliminates
    1.54
     eliminate
    1.49
     eliminating
    1.48
     avoids
    1.45
     reduces
    1.45
     reduce
    1.44
    elimin
    1.42
     reducing
    1.41
    Activations Density 1.446%

    No Known Activations