© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 4012
    Prev
    Next
    INDEX
    Explanations

    concepts related to T cell activation and differentiation in immunology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.56
    DispatchToProps
    -0.55
    lijf
    -0.53
    IBOutlet
    -0.52
    /******/
    -0.52
    மை
    -0.51
    oneofs
    -0.51
    scrapy
    -0.49
    Personendaten
    -0.48
     Insee
    -0.48
    POSITIVE LOGITS
    \{\\
    0.71
     CD
    0.70
     memory
    0.66
    CD
    0.64
     Memory
    0.59
     DCs
    0.58
     expansion
    0.58
     recall
    0.56
     MEMORY
    0.56
    tvguidetime
    0.55
    Activations Density 1.446%

    No Known Activations