© 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. 21-GEMMASCOPE-RES-16K
    6. 12256
    Prev
    Next
    INDEX
    Explanations

    references to parasites in a biological or medical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.68
    NameInMap
    -0.60
    存于互联网档案馆
    -0.55
     يتيمه
    -0.54
     crossorigin
    -0.53
     duchess
    -0.52
     Albe
    -0.52
    istoitu
    -0.51
     bellows
    -0.51
     Domino
    -0.51
    POSITIVE LOGITS
     parasite
    1.20
     Paras
    1.16
     parasites
    1.13
     parasitic
    1.09
     paras
    1.08
    Paras
    1.06
    paras
    0.99
     worm
    0.87
    寄生
    0.82
    asitic
    0.81
    Activations Density 0.756%

    No Known Activations