© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 844
    Prev
    Next
    INDEX
    Explanations

    phrases that denote perspectives or viewpoints

    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
     from
    -0.94
     از
    -0.76
    從
    -0.71
    从
    -0.66
     dari
    -0.63
     từ
    -0.63
     kutoka
    -0.60
     desde
    -0.57
     siitä
    -0.52
    从中
    -0.51
    POSITIVE LOGITS
     standpoint
    1.02
     perspective
    0.93
     onwards
    0.88
     sources
    0.82
     Perspective
    0.68
     vantage
    0.68
     onward
    0.68
    perspective
    0.66
     viewpoint
    0.64
    Perspective
    0.63
    Activations Density 0.585%

    No Known Activations