Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 8113
    Prev
    Next
    INDEX
    Explanations

    terms related to anesthesia and surgical procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -1.02
     SqlCommand
    -0.79
    PerformLayout
    -0.74
     AssemblyTitle
    -0.73
    amaño
    -0.68
    mappedBy
    -0.66
    latego
    -0.66
    GEBURTSDATUM
    -0.66
    Vidite
    -0.61
     BorderRadius
    -0.60
    POSITIVE LOGITS
     mode
    0.67
     Mode
    0.58
     modes
    0.56
    Mode
    0.56
     phase
    0.55
     state
    0.55
     режим
    0.54
    enter
    0.53
     deep
    0.52
    状態
    0.49
    Activations Density 0.412%

    No Known Activations