© 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. 18-GEMMASCOPE-RES-16K
    11. 2936
    Prev
    Next
    INDEX
    Explanations

    information related to immune system conditions and infections

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

    the immune system

    np_acts-logits-general · gemini-2.0-flash

    immune system functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    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
    -0.52
     Prince
    -0.48
     artifact
    -0.48
     splinter
    -0.47
    ConverterFactory
    -0.46
    Otp
    -0.45
    зер
    -0.44
    zí
    -0.44
    manfaat
    -0.44
     Peralta
    -0.44
    POSITIVE LOGITS
     immune
    1.62
     immuno
    1.43
     Immune
    1.42
     immunosupp
    1.41
     immun
    1.32
     immunity
    1.30
    Immun
    1.28
     inmun
    1.26
    Immune
    1.26
    immun
    1.24
    Activations Density 0.242%

    No Known Activations