© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 2770
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
    Negative Logits
    IsContent
    -0.56
    bootstrapcdn
    -0.51
    amsmath
    -0.50
    AsUp
    -0.49
    tagHelperRunner
    -0.49
     Picchu
    -0.46
    StartTag
    -0.44
     intptr
    -0.43
    LEncoder
    -0.43
    🦵
    -0.42
    POSITIVE LOGITS
     include
    0.49
    StoryboardSegue
    0.48
     includes
    0.42
    Secondly
    0.42
     außerdem
    0.41
     նաև
    0.41
    在于
    0.41
    Especially
    0.41
     consiste
    0.40
    NextPage
    0.40
    Activations Density 0.468%

    No Known Activations