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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 17-GEMMASCOPE-RES-16K
    6. 5277
    Prev
    Next
    INDEX
    Explanations

    terms related to inflammatory responses and cytokines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yarnpkg
    -0.51
    __*/
    -0.49
    loem
    -0.47
    omyelitis
    -0.46
     Freitas
    -0.45
    npmjs
    -0.45
    atitis
    -0.44
    grafic
    -0.44
    ナップ
    -0.44
     متعلقه
    -0.44
    POSITIVE LOGITS
     receptors
    1.09
     receptor
    1.04
     Receptors
    1.02
     Receptor
    0.94
     recepto
    0.84
    receptor
    0.83
    ThroughAttribute
    0.77
     recept
    0.74
    InjectAttribute
    0.73
     рецеп
    0.72
    Activations Density 1.314%

    No Known Activations