© 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. 40-GEMMASCOPE-RES-16K
    11. 3734
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between concepts or entities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -0.62
    
    -0.61
    queryInterface
    -0.49
    #+#
    -0.48
     CURIAM
    -0.48
    ResponseWriter
    -0.47
    uxxxx
    -0.46
    ViewImports
    -0.46
    EndGlobalSection
    -0.45
    RenderAtEndOf
    -0.45
    POSITIVE LOGITS
     between
    4.56
    between
    3.77
    Between
    3.66
     Between
    3.66
     между
    3.45
     zwischen
    3.44
     tussen
    3.22
     mellan
    3.05
     між
    3.02
     mellom
    2.89
    Activations Density 3.218%

    No Known Activations