© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 2265
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax and function calls related to data handling and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    momix
    -0.53
    lè
    -0.52
    (${
    -0.48
    quot
    -0.47
    -
    -0.47
     pylab
    -0.47
    σου
    -0.47
     respecte
    -0.46
    '
    -0.45
    \#
    -0.45
    POSITIVE LOGITS
     &
    1.70
     \&
    1.09
     &,
    0.97
     &.
    0.95
     &[
    0.91
     &\
    0.87
     &_
    0.81
     незавершена
    0.81
     estekak
    0.78
     &(
    0.73
    Activations Density 0.206%

    No Known Activations