© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10874
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the significance of specific nouns or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "[the] [noun]" pattern

    np_acts-logits-general · gemini-2.0-flash

    specific concepts or items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    راد
    -0.51
     ComVisible
    -0.47
    Vinc
    -0.45
     Chwiliwch
    -0.44
    AlterField
    -0.43
     hesitating
    -0.43
    lani
    -0.43
    IBAction
    -0.41
     autorytatywna
    -0.41
    copo
    -0.41
    POSITIVE LOGITS
     phenomenon
    0.93
     genre
    0.92
     fenomeno
    0.80
     phénomène
    0.78
     technique
    0.71
     modality
    0.70
     phenomena
    0.70
     malady
    0.67
     fenómeno
    0.66
    artige
    0.65
    Activations Density 0.412%

    No Known Activations