© 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. 169
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical instructions and treatments

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

    after articles ("a", "the") and prepositions ("for", "of", "into")

    np_acts-logits-general · gemini-2.0-flash

    damaged and dysfunctional states

    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
    なもの
    -0.52
     direta
    -0.47
    neither
    -0.46
     assise
    -0.44
    something
    -0.43
     stør
    -0.43
     majeurs
    -0.43
     natürlichen
    -0.42
    worldwide
    -0.41
     jähr
    -0.41
    POSITIVE LOGITS
     damaged
    1.21
     newly
    1.15
     injured
    1.06
     freshly
    1.03
     repaired
    1.03
     bombed
    1.03
     affected
    1.02
     infected
    1.00
     destroyed
    0.99
     stricken
    0.99
    Activations Density 1.169%

    No Known Activations