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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 4041
    Prev
    Next
    INDEX
    Explanations

    references to immune system cells and their functions, particularly B cells and their role in antibody production

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

    B cells and antibody genes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.57
     informée
    -0.53
     CanadaChoose
    -0.51
    évaluateur
    -0.51
    /******/
    -0.50
     Signalez
    -0.49
    
    -0.48
    EndProject
    -0.43
    TAWA
    -0.42
    phyr
    -0.41
    POSITIVE LOGITS
     immunoglobulin
    0.64
     IgM
    0.64
     antibody
    0.62
    oglobulin
    0.60
     Antibody
    0.54
    Antibody
    0.52
     antibodies
    0.46
     IgG
    0.45
     inmun
    0.45
     follicles
    0.44
    Activations Density 0.132%

    No Known Activations