© 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. 67
    Prev
    Next
    INDEX
    Explanations

    references to policies and requirements related to healthcare and reproductive rights

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

    after "voted" or related to "support"

    np_acts-logits-general · gemini-2.0-flash

    support or voting against

    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
    Földrajzportál
    -0.54
     bruto
    -0.53
    脚注の使い方
    -0.51
     häm
    -0.50
     mattino
    -0.50
    BufferException
    -0.50
     HttpNotFound
    -0.49
    ließlich
    -0.48
    ็จ
    -0.48
    chables
    -0.48
    POSITIVE LOGITS
     support
    1.67
     supports
    1.57
     supporting
    1.52
     Support
    1.43
    support
    1.42
     SUPPORT
    1.41
     Supports
    1.41
     supported
    1.39
    Support
    1.38
    supporting
    1.37
    Activations Density 0.768%

    No Known Activations