© 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. 4-GEMMASCOPE-RES-16K
    11. 10611
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to medical conditions, health issues, and references to health treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -1.29
    AndroidJUnit
    -0.92
    帖最后由
    -0.88
     crdi
    -0.88
    jspx
    -0.84
     springfox
    -0.83
    __":
    -0.82
    MigrationBuilder
    -0.81
    
    -0.80
     transfieras
    -0.79
    POSITIVE LOGITS
     Silverman
    0.76
    itext
    0.73
    Alexandre
    0.73
     Alexandre
    0.73
     Loud
    0.72
     pendants
    0.70
     Nix
    0.70
     Nam
    0.69
     Igu
    0.68
     Bryson
    0.68
    Activations Density 9.709%

    No Known Activations