© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4004
    Prev
    Next
    INDEX
    Explanations

    phrases related to genetic and clinical factors influencing health outcomes

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

    after "responsible," "explain," or "for."

    np_acts-logits-general · gemini-2.0-flash

    driving success

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الدراسه
    -0.72
     دیکھیے
    -0.66
    NameInMap
    -0.63
     Administrativna
    -0.61
     архивлан
    -0.60
    styleType
    -0.58
     vVar
    -0.55
    TemporalType
    -0.55
     AssemblyProduct
    -0.55
     grà
    -0.55
    POSITIVE LOGITS
     success
    0.97
     why
    0.83
     successful
    0.81
     observed
    0.77
     successo
    0.75
     успеха
    0.73
     succès
    0.73
     meeste
    0.73
    successful
    0.71
     meisten
    0.71
    Activations Density 0.709%

    No Known Activations