© 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. 38-GEMMASCOPE-RES-16K
    11. 13913
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific proposals and experimental setups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fds
    -0.33
    cano
    -0.33
    ceğ
    -0.32
     stump
    -0.32
     karş
    -0.31
    шти
    -0.31
     ostavi
    -0.31
    MethodImpl
    -0.31
     البر
    -0.30
    ens
    -0.30
    POSITIVE LOGITS
     beam
    0.84
    setVerticalGroup
    0.76
    AccessorTable
    0.75
     accelerator
    0.75
     AssemblyCulture
    0.73
     Beam
    0.73
    SharedDtor
    0.67
     accelerators
    0.66
    beam
    0.66
    Beam
    0.65
    Activations Density 0.604%

    No Known Activations