© 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. 40-GEMMASCOPE-RES-16K
    11. 7038
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology, specifically networking and innovations in quantum computing

    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
    ftagPool
    -0.54
    StructEnd
    -0.46
     kasarigan
    -0.45
    MessageOf
    -0.42
    AsUp
    -0.41
     remonter
    -0.40
    MenuInflater
    -0.39
     تضيفلها
    -0.39
    addGap
    -0.38
    secuencias
    -0.37
    POSITIVE LOGITS
     prototype
    1.95
     prototypes
    1.85
     pilot
    1.78
     trial
    1.59
     Prototype
    1.56
     trials
    1.52
     piloto
    1.51
     prototyping
    1.51
    pilot
    1.48
     demonstration
    1.48
    Activations Density 1.056%

    No Known Activations