© 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. 22-GEMMASCOPE-RES-16K
    11. 2232
    Prev
    Next
    INDEX
    Explanations

    phrases related to biological processes and molecular interactions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    preceding prepositions (for, in, of, to)

    np_acts-logits-general · gemini-2.0-flash

    prepositions and articles followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     CreateTagHelper
    -0.88
    awtextra
    -0.84
    WebVitals
    -0.83
     pinulongan
    -0.81
     faptul
    -0.81
     typelib
    -0.79
     ſeveral
    -0.79
     femininas
    -0.77
     defaultstate
    -0.77
     brancas
    -0.76
    POSITIVE LOGITS
     etc
    0.68
    ).
    0.68
    Спољашње
    0.65
    ?).
    0.62
     "").
    0.58
    Enllaces
    0.58
     ).
    0.57
     otherwise
    0.57
    ')}}">
    0.55
    .
    0.55
    Activations Density 2.550%

    No Known Activations