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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7432
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to medical interventions, specifically those targeting cancer and related therapies

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

    Targeting or modulating genes/receptors

    np_acts-logits-general · gemini-2.0-flash

    biological targeting and modulation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     considérons
    -0.46
    +#+
    -0.36
    áctenos
    -0.35
     journées
    -0.34
    довлет
    -0.33
     réfé
    -0.33
     roupa
    -0.33
     resourceCulture
    -0.32
     légal
    -0.32
    Ekster
    -0.31
    POSITIVE LOGITS
     DNA
    0.91
     gene
    0.88
     genes
    0.87
     molecular
    0.83
     RNA
    0.78
     mRNA
    0.77
    DNA
    0.75
     dna
    0.72
     biochemistry
    0.70
     proteins
    0.69
    Activations Density 2.726%

    No Known Activations