© 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. 18-GEMMASCOPE-RES-16K
    6. 3906
    Prev
    Next
    INDEX
    Explanations

    terms related to drug delivery and medical treatments involving antibodies

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

    Formation of protein or antibody complexes

    np_acts-logits-general · gemini-2.0-flash

    antibody protein complex binding

    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
     flamma
    -0.58
     sawing
    -0.56
     TextInputType
    -0.56
     cran
    -0.54
     ujednoznacz
    -0.54
     earthen
    -0.52
     ston
    -0.52
     gypsum
    -0.52
    makeConstraints
    -0.51
     quema
    -0.50
    POSITIVE LOGITS
     binding
    1.17
     Binding
    0.93
     bind
    0.89
     protein
    0.87
    Binding
    0.86
    binding
    0.85
     bound
    0.84
     binds
    0.81
     interaction
    0.80
     complexes
    0.77
    Activations Density 2.628%

    No Known Activations