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

    Neuronpedia

    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. 28-GEMMASCOPE-RES-16K
    11. 4063
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to technical and scientific concepts in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "in [a specific topic]"

    np_acts-logits-general · gemini-2.0-flash

    nationalities and rural locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pouvoit
    -0.50
     avoient
    -0.50
     solches
    -0.49
     auroit
    -0.49
     moindre
    -0.49
     whoever
    -0.48
     hvilken
    -0.47
     malheur
    -0.47
     altså
    -0.47
     overras
    -0.47
    POSITIVE LOGITS
     modern
    0.71
     contemporary
    0.62
     Nigerian
    0.58
     Korean
    0.57
     rural
    0.57
     Modern
    0.55
     Canadian
    0.55
     Indian
    0.54
     Chinese
    0.53
     Brazilian
    0.53
    Activations Density 1.448%

    No Known Activations