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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 10412
    Prev
    Next
    INDEX
    Explanations

    references to 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 @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مجه
    -0.54
    equipped
    -0.53
     Equipped
    -0.51
     equipped
    -0.50
    Equipped
    -0.48
    onAttach
    -0.44
     equipado
    -0.42
    tagHelperRunner
    -0.41
     métodos
    -0.38
     resourceCulture
    -0.38
    POSITIVE LOGITS
     perspective
    1.09
     Perspective
    0.91
     perspectives
    0.90
    perspective
    0.87
     PERSPECT
    0.86
    Perspective
    0.80
     Perspectives
    0.77
     perspectiva
    0.76
    Perspectives
    0.69
     perspectivas
    0.62
    Activations Density 0.110%

    No Known Activations