© 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. 5-GEMMASCOPE-RES-16K
    6. 6347
    Prev
    Next
    INDEX
    Explanations

    terms related to immune response and cell interaction in the context of disease

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.70
    /***/
    -0.63
    DockStyle
    -0.58
     maxlength
    -0.58
     Petru
    -0.57
     виправивши
    -0.57
     Frat
    -0.56
     Sine
    -0.56
    bentar
    -0.55
     beaten
    -0.55
    POSITIVE LOGITS
     immune
    0.86
     Immunol
    0.84
     Immune
    0.80
     Immunology
    0.77
     lymphocyte
    0.76
    Immune
    0.73
     lymphocytes
    0.71
     immunity
    0.68
     имму
    0.68
     Immunity
    0.68
    Activations Density 0.997%

    No Known Activations