© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5356
    Prev
    Next
    INDEX
    Explanations

    references to the parameters or arguments passed in methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
     M
    -0.51
     ‘
    -0.50
     
    -0.49
     [
    -0.49
     and
    -0.48
    <eos>
    -0.47
     “
    -0.46
    ity
    -0.46
     &
    -0.46
     C
    -0.45
    POSITIVE LOGITS
    ArgsConstructor
    1.78
    PerformLayout
    1.26
     args
    1.23
    EndInit
    1.10
    AddTagHelper
    1.10
    ArgumentParser
    1.08
    RenderAtEndOf
    1.03
     CreateTagHelper
    1.00
    SerializeField
    0.99
     Arguments
    0.99
    Activations Density 0.027%

    No Known Activations