© 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 EvalsExportsAPI 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. 4742
    Prev
    Next
    INDEX
    Explanations

    phrases related to innovation and the generation of new ideas

    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
     concept
    -0.59
    concept
    -0.56
     SEDS
    -0.54
     Concept
    -0.52
    principle
    -0.49
    findpost
    -0.48
     principle
    -0.48
    makeConstraints
    -0.47
    idea
    -0.47
     premise
    -0.47
    POSITIVE LOGITS
     concepts
    1.33
     topics
    1.23
     ideas
    1.19
     Concepts
    1.08
     Topics
    1.00
    Concepts
    0.98
     Ideas
    0.97
    concepts
    0.95
     CONCEPTS
    0.94
    Topics
    0.92
    Activations Density 0.082%

    No Known Activations