© 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. 7297
    Prev
    Next
    INDEX
    Explanations

    words related to education and community impact

    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
     itſelf
    -0.69
     itself
    -0.63
    itself
    -0.62
     dAtA
    -0.61
    SequentialGroup
    -0.61
     EconPapers
    -0.57
    檚
    -0.55
    reciated
    -0.55
    ISupport
    -0.54
    igy
    -0.54
    POSITIVE LOGITS
     who
    1.01
    hips
    0.96
     themselves
    0.90
     którzy
    0.80
     ktorí
    0.79
     kteří
    0.78
    hip
    0.72
     whom
    0.71
     الذين
    0.69
    们的
    0.69
    Activations Density 0.717%

    No Known Activations