© 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. 15-GEMMASCOPE-RES-16K
    11. 3007
    Prev
    Next
    INDEX
    Explanations

    descriptions of variation or differences in data and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.57
    Predecesor
    -0.47
    NUMX
    -0.44
     ferment
    -0.44
    udin
    -0.43
    舺
    -0.43
    género
    -0.42
    cendo
    -0.42
     دیکھیے
    -0.42
    infect
    -0.42
    POSITIVE LOGITS
     receive
    0.66
     bekommen
    0.64
     receives
    0.63
     obtains
    0.60
     get
    0.60
     получите
    0.60
     получают
    0.60
     received
    0.60
     bekommt
    0.60
     krijgen
    0.59
    Activations Density 0.520%

    No Known Activations