© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 13324
    Prev
    Next
    INDEX
    Explanations

    terms indicating evidence or results in scientific contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     كومونز
    -0.70
    Geplaatst
    -0.50
    פת
    -0.49
    kere
    -0.48
    webElementXpaths
    -0.47
     estat
    -0.45
    InView
    -0.45
    through
    -0.41
    EndContext
    -0.41
     ins
    -0.41
    POSITIVE LOGITS
     indicate
    1.65
    indicate
    1.49
     Indicate
    1.35
     indicates
    1.27
    indicates
    1.26
     signify
    1.24
     indicating
    1.13
     denote
    1.12
     suggest
    1.11
     Indicates
    1.08
    Activations Density 0.200%

    No Known Activations