© 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. 28-GEMMASCOPE-RES-16K
    11. 12019
    Prev
    Next
    INDEX
    Explanations

    references to the private sector and non-profit organizations in the context of healthcare and education

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

    following "or"

    np_acts-logits-general · gemini-2.0-flash

    voluntary contributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     renouvel
    -0.40
     suprême
    -0.39
     liné
    -0.36
     boyunca
    -0.35
     nucléaire
    -0.32
     Broadcast
    -0.32
     embl
    -0.32
    sprogramm
    -0.31
    Animated
    -0.31
    Scheduled
    -0.31
    POSITIVE LOGITS
     privately
    1.52
     private
    1.52
     prywat
    1.29
     privat
    1.23
     privaten
    1.21
    private
    1.20
     PRIVATE
    1.20
     privato
    1.20
     privata
    1.19
     Private
    1.16
    Activations Density 0.750%

    No Known Activations