© 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. 27-GEMMASCOPE-RES-16K
    11. 9821
    Prev
    Next
    INDEX
    Explanations

    specific terms related to diagnostics and medical markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.44
    :][
    -0.43
     considérons
    -0.40
     rimasto
    -0.40
    ustris
    -0.40
    griffe
    -0.39
     uważ
    -0.39
     formada
    -0.39
     منها
    -0.39
     caminando
    -0.39
    POSITIVE LOGITS
    MigrationBuilder
    0.53
     الحره
    0.49
    HomeAsUpEnabled
    0.47
     cherchés
    0.42
     kasarigan
    0.41
     offering
    0.41
     whereby
    0.41
     provider
    0.41
     worthy
    0.40
     usable
    0.40
    Activations Density 0.524%

    No Known Activations