© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4799
    Prev
    Next
    INDEX
    Explanations

    technical terms related to antibodies and immunological assays

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

    Antibodies or antibody-related terms

    np_acts-logits-general · gemini-2.0-flash

    antibody or anti-antibody

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     charter
    -0.44
    뀔
    -0.38
     horror
    -0.36
    تقاوى
    -0.35
    pageX
    -0.35
     hvil
    -0.35
    뀝
    -0.34
    RelativeTo
    -0.33
     Charter
    -0.33
    Charter
    -0.33
    POSITIVE LOGITS
     antibodies
    1.09
     Antibodies
    0.94
    Antibodies
    0.90
     antibody
    0.89
     Antibody
    0.75
    Antibody
    0.66
    TypedDataSet
    0.66
     monoclonal
    0.65
    LabelTagHelper
    0.58
     IgG
    0.57
    Activations Density 1.202%

    No Known Activations