© 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. 38-GEMMASCOPE-RES-16K
    11. 9986
    Prev
    Next
    INDEX
    Explanations

    various aspects and characteristics related to devices and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -1.11
     kaarangay
    -0.76
     itself
    -0.73
     itſelf
    -0.72
     enfans
    -0.63
    itself
    -0.61
    SourceChecksum
    -0.61
    Autoritní
    -0.61
    MLLoader
    -0.59
    httphttps
    -0.59
    POSITIVE LOGITS
     themselves
    1.06
    hips
    0.84
    capes
    0.84
     которые
    0.77
     galore
    0.76
    themselves
    0.71
    heets
    0.71
    ystems
    0.69
    hirts
    0.65
    ystemen
    0.64
    Activations Density 2.700%

    No Known Activations