© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 634
    Prev
    Next
    INDEX
    Explanations

    references to the World Health Organization and its classifications related to health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.54
    ➟
    -0.44
    enterOuterAlt
    -0.44
    errHandler
    -0.43
    fjspx
    -0.42
    Filmografie
    -0.42
    romyalgia
    -0.41
    ínica
    -0.41
     discomfort
    -0.41
     FFA
    -0.41
    POSITIVE LOGITS
    WHO
    0.63
     WHO
    0.59
     malaria
    0.43
     linkovi
    0.43
     estekak
    0.42
    Aholisi
    0.40
     Malaria
    0.40
     programme
    0.40
    oneofs
    0.39
    kesmas
    0.39
    Activations Density 0.595%

    No Known Activations