Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 7931
    Prev
    Next
    INDEX
    Explanations

    terms related to mastitis, particularly in veterinary contexts

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

    The token "Mas" or "mas"

    np_acts-logits-general · gemini-2.0-flash

    mastitis following Mas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    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
    -0.68
    FormTagHelper
    -0.60
    thys
    -0.59
     stedet
    -0.55
     createSprite
    -0.54
    bben
    -0.54
     Dernière
    -0.52
    发表于
    -0.52
    uyla
    -0.52
    exus
    -0.52
    POSITIVE LOGITS
     Mas
    0.99
    Mas
    0.86
     mas
    0.74
    IonicModule
    0.66
     ModelExpression
    0.65
     MAS
    0.64
    ParallelGroup
    0.58
    Enllaces
    0.56
     Wiktionnaire
    0.55
    MAS
    0.52
    Activations Density 0.127%

    No Known Activations