© 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. 36-GEMMASCOPE-RES-16K
    11. 9788
    Prev
    Next
    INDEX
    Explanations

    specific phrases indicating regulations, requirements, or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    various
    -0.50
    enumi
    -0.48
     demás
    -0.48
    Various
    -0.46
     Various
    -0.45
     respectivos
    -0.45
     respectivas
    -0.44
     verschiedenen
    -0.43
     rağmen
    -0.43
    也好
    -0.42
    POSITIVE LOGITS
     situations
    1.17
     areas
    1.02
     items
    1.01
     entities
    0.94
     environments
    0.88
     creatures
    0.88
     things
    0.85
     sites
    0.84
     topics
    0.83
     olyan
    0.83
    Activations Density 1.908%

    No Known Activations