© 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. 3-GEMMASCOPE-RES-16K
    11. 8632
    Prev
    Next
    INDEX
    Explanations

    references to specific terms, particularly those that are abbreviations, proper nouns, or unique identifiers

    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
     orçamento
    -0.36
    Текст
    -0.36
     energético
    -0.36
    DispatchToProps
    -0.35
    HasKey
    -0.34
     poffible
    -0.34
     retrô
    -0.34
     PM
    -0.34
    readFileSync
    -0.33
     Rock
    -0.33
    POSITIVE LOGITS
    ub
    0.93
    UB
    0.84
     Dub
    0.69
    Dub
    0.68
     dub
    0.65
    Географиясе
    0.63
     <<<<<<<<<<<<<<
    0.63
    ubs
    0.61
    Jeografia
    0.60
     Hub
    0.58
    Activations Density 1.348%

    No Known Activations