© 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. 22-GEMMASCOPE-RES-16K
    11. 8139
    Prev
    Next
    INDEX
    Explanations

    terms related to antibody assays and immunological experiments

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

    Secondary antibody labeling in experiments

    np_acts-logits-general · gemini-2.0-flash

    anti antibody

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wireType
    -0.65
    сылкі
    -0.64
    Datuak
    -0.63
    Parcelize
    -0.60
     sidewalk
    -0.59
    HomeAsUpEnabled
    -0.59
    ymce
    -0.57
     Aceh
    -0.55
     Teflon
    -0.54
     scooters
    -0.54
    POSITIVE LOGITS
     antibodies
    1.32
     antibody
    1.26
     Antibodies
    1.08
     anti
    1.07
     monoclonal
    0.98
     Antibody
    0.98
    anti
    0.98
     IgG
    0.96
    Antibodies
    0.94
    Antibody
    0.92
    Activations Density 1.248%

    No Known Activations