© 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. 8272
    Prev
    Next
    INDEX
    Explanations

    questions about options and alternatives

    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
     respectively
    -0.91
    respectively
    -0.84
     respectivamente
    -0.82
     respectivement
    -0.72
    respective
    -0.55
    分別
    -0.54
     respective
    -0.54
    Together
    -0.51
    分别
    -0.51
    それぞれ
    -0.50
    POSITIVE LOGITS
     both
    0.97
     cả
    0.72
     både
    0.70
     zowel
    0.69
    ทั้ง
    0.66
    both
    0.64
     양
    0.62
     zarówno
    0.60
     sowohl
    0.60
     oth
    0.59
    Activations Density 0.165%

    No Known Activations