© 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. 7835
    Prev
    Next
    INDEX
    Explanations

    instances of unusual or unexpected events or phenomena

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

    after specific verbs ("retrieve", "heard")

    np_acts-logits-general · gemini-2.0-flash

    retrieve or surrounding words

    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
    vereignty
    -0.51
     silos
    -0.50
     vineyards
    -0.50
     sabre
    -0.50
     aspirants
    -0.49
    LabelTagHelper
    -0.49
     fieldNum
    -0.48
    ditto
    -0.48
     Houſe
    -0.48
     clinics
    -0.47
    POSITIVE LOGITS
    enumi
    0.41
     propOrder
    0.40
     makeshift
    0.40
     sozinho
    0.36
     semejante
    0.35
     unintended
    0.35
    breng
    0.35
     inesperado
    0.35
     contra
    0.35
    Referències
    0.34
    Activations Density 0.367%

    No Known Activations