© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 15750
    Prev
    Next
    INDEX
    Explanations

    expressions related to storytelling from multiple perspectives

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "From [a/the]" or "point of view/perspective"

    np_acts-logits-general · gemini-2.0-flash

    perspective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    々と
    -0.36
     Sandy
    -0.36
    Ծանոթ
    -0.35
    lántico
    -0.34
    клопе
    -0.34
    المكان
    -0.34
    ็จ
    -0.33
    Pix
    -0.33
    Weblinks
    -0.33
    Sandy
    -0.32
    POSITIVE LOGITS
     perspective
    2.45
     perspectives
    2.02
     viewpoint
    2.00
    perspective
    1.95
     Perspective
    1.92
     PERSPECT
    1.83
     perspectiva
    1.80
    Perspective
    1.76
     perspek
    1.69
     viewpoints
    1.67
    Activations Density 0.481%

    No Known Activations