© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12298
    Prev
    Next
    INDEX
    Explanations

    research related to cancer and its treatment mechanisms in various species

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

    "in" followed by a reference to people

    np_acts-logits-general · gemini-2.0-flash

    demographic health categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trouvez
    -0.48
     étrangères
    -0.44
     extérieurs
    -0.43
     znamen
    -0.42
    enta
    -0.40
     معرف
    -0.40
     utiles
    -0.39
    áh
    -0.39
    core
    -0.39
     SqlDbType
    -0.37
    POSITIVE LOGITS
     patients
    1.03
     humans
    1.02
     adults
    0.97
     healthy
    0.94
     individuals
    0.83
     young
    0.80
    InitVars
    0.78
     athletes
    0.78
    Portale
    0.77
     infants
    0.76
    Activations Density 1.389%

    No Known Activations