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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 13000
    Prev
    Next
    INDEX
    Explanations

    instances of health-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     washes
    -0.49
     Fürst
    -0.49
    minimum
    -0.48
    Minimum
    -0.48
     Minimal
    -0.48
    true
    -0.48
    GroupLayout
    -0.46
     Minimum
    -0.46
    BagLayout
    -0.46
    Gesch
    -0.46
    POSITIVE LOGITS
     consultato
    0.85
    WebVitals
    0.77
    UrlResolution
    0.74
     alive
    0.70
     Alive
    0.65
    SharedDtor
    0.61
     ALIVE
    0.60
     <<<<<<<<<<<<<<
    0.60
     vivos
    0.59
     resourceCulture
    0.59
    Activations Density 0.773%

    No Known Activations